Authors: Chenyi Cai, Kosuke Kuriyama, Youlong Gu, Filip Biljecki, Pieter Herthogs
Abstract: Urban street environments are vital to supporting human activity in public spaces. The emergence of big data, such as street view images (SVIs) combined with multimodal large language models (MLLMs), is transforming how researchers and practitioners investigate, measure, and evaluate semantic and visual elements of urban environments. Considering the low threshold for creating automated evaluative workflows using MLLMs, it is crucial to explore both the risks and opportunities associated with these probabilistic models. In particular, the extent to which the integration of expert knowledge can influence the performance of MLLMs in evaluating the quality of urban design has not been fully explored. This study sets out an initial exploration of how integrating more formal and structured representations of expert urban design knowledge into the input prompts of an MLLM (ChatGPT-4) can enhance the model's capability and reliability in evaluating the walkability of built environments using SVIs. We collect walkability metrics from the existing literature and categorize them using relevant ontologies. We then select a subset of these metrics, focusing on the subthemes of pedestrian safety and attractiveness, and develop prompts for the MLLM accordingly. We analyze the MLLM's ability to evaluate SVI walkability subthemes through prompts with varying levels of clarity and specificity regarding evaluation criteria. Our experiments demonstrate that MLLMs are capable of providing assessments and interpretations based on general knowledge and can support the automation of multimodal image-text evaluations. However, they generally provide more optimistic scores and can make mistakes when interpreting the provided metrics, resulting in incorrect evaluations. By integrating expert knowledge, the MLLM's evaluative performance exhibits higher consistency and concentration.
Authors: Murali Ramanujam, Yinwei Dai, Kyle Jamieson, Ravi Netravali
Abstract: Continually retraining models has emerged as a primary technique to enable high-accuracy video analytics on edge devices. Yet, existing systems employ such adaptation by relying on the spare compute resources that traditional (memory-constrained) edge servers afford. In contrast, mobile edge devices such as drones and dashcams offer a fundamentally different resource profile: weak(er) compute with abundant unified memory pools. We present Legilimens, a continuous learning system for the mobile edge's System-on-Chip GPUs. Our driving insight is that visually distinct scenes that require retraining exhibit substantial overlap in model embeddings; if captured into a base model on device memory, specializing to each new scene can become lightweight, requiring very few samples. To practically realize this approach, Legilimens presents new, compute-efficient techniques to (1) select high-utility data samples for retraining specialized models, (2) update the base model without complete retraining, and (3) time-share compute resources between retraining and live inference for maximal accuracy. Across diverse workloads, Legilimens lowers retraining costs by 2.8-10x compared to existing systems, resulting in 18-45% higher accuracies.
Authors: Muhammad Turab, Philippe Colantoni, Damien Muselet, Alain Tremeau
Abstract: This paper presents a novel framework for emotion recognition in contemporary dance by improving existing Laban Movement Analysis (LMA) feature descriptors and introducing robust, novel descriptors that capture both quantitative and qualitative aspects of the movement. Our approach extracts expressive characteristics from 3D keypoints data of professional dancers performing contemporary dance under various emotional states, and trains multiple classifiers, including Random Forests and Support Vector Machines. Additionally, we provide in-depth explanation of features and their impact on model predictions using explainable machine learning methods. Overall, our study improves emotion recognition in contemporary dance and offers promising applications in performance analysis, dance training, and human--computer interaction, with a highest accuracy of 96.85\%.
Authors: Muhammad Turab, Philippe Colantoni, Damien Muselet, Alain Tremeau
Abstract: The growing interest in automated movement analysis has presented new challenges in recognition of complex human activities including dance. This study focuses on dance style recognition using features extracted using Laban Movement Analysis. Previous studies for dance style recognition often focus on cross-frame movement analysis, which limits the ability to capture temporal context and dynamic transitions between movements. This gap highlights the need for a method that can add temporal context to LMA features. For this, we introduce a novel pipeline which combines 3D pose estimation, 3D human mesh reconstruction, and floor aware body modeling to effectively extract LMA features. To address the temporal limitation, we propose a sliding window approach that captures movement evolution across time in features. These features are then used to train various machine learning methods for classification, and their explainability explainable AI methods to evaluate the contribution of each feature to classification performance. Our proposed method achieves a highest classification accuracy of 99.18\% which shows that the addition of temporal context significantly improves dance style recognition performance.
Authors: Vedika Srivastava, Hemant Kumar Singh, Jaisal Singh
Abstract: This paper presents a novel approach to geolocating images captured from the International Space Station (ISS) using advanced machine learning algorithms. Despite having precise ISS coordinates, the specific Earth locations depicted in astronaut-taken photographs often remain unidentified. Our research addresses this gap by employing three distinct image processing pipelines: a Neural Network based approach, a SIFT based method, and GPT-4 model. Each pipeline is tailored to process high-resolution ISS imagery, identifying both natural and man-made geographical features. Through extensive evaluation on a diverse dataset of over 140 ISS images, our methods demonstrate significant promise in automated geolocation with varied levels of success. The NN approach showed a high success rate in accurately matching geographical features, while the SIFT pipeline excelled in processing zoomed-in images. GPT-4 model provided enriched geographical descriptions alongside location predictions. This research contributes to the fields of remote sensing and Earth observation by enhancing the accuracy and efficiency of geolocating space-based imagery, thereby aiding environmental monitoring and global mapping efforts.
Authors: Jiaqi Liu, Ran Tong, Aowei Shen, Shuzheng Li, Changlin Yang, Lisha Xu
Abstract: Memes often merge visuals with brief text to share humor or opinions, yet some memes contain harmful messages such as hate speech. In this paper, we introduces MemeBLIP2, a light weight multimodal system that detects harmful memes by combining image and text features effectively. We build on previous studies by adding modules that align image and text representations into a shared space and fuse them for better classification. Using BLIP-2 as the core vision-language model, our system is evaluated on the PrideMM datasets. The results show that MemeBLIP2 can capture subtle cues in both modalities, even in cases with ironic or culturally specific content, thereby improving the detection of harmful material.
Authors: Manikanta Varaganti, Amulya Vankayalapati, Nour Awad, Gregory R. Dion, Laura J. Brattain
Abstract: Neck ultrasound (US) plays a vital role in airway management by providing non-invasive, real-time imaging that enables rapid and precise interventions. Deep learning-based anatomical landmark detection in neck US can further facilitate procedural efficiency. However, class imbalance within datasets, where key structures like tracheal rings and vocal folds are underrepresented, presents significant challenges for object detection models. To address this, we propose T2ID-CAS, a hybrid approach that combines a text-to-image latent diffusion model with class-aware sampling to generate high-quality synthetic samples for underrepresented classes. This approach, rarely explored in the ultrasound domain, improves the representation of minority classes. Experimental results using YOLOv9 for anatomical landmark detection in neck US demonstrated that T2ID-CAS achieved a mean Average Precision of 88.2, significantly surpassing the baseline of 66. This highlights its potential as a computationally efficient and scalable solution for mitigating class imbalance in AI-assisted ultrasound-guided interventions.
Authors: Yangyang Qu, Dazhi Fu, Jicong Fan
Abstract: Unsupervised novelty detection (UND), aimed at identifying novel samples, is essential in fields like medical diagnosis, cybersecurity, and industrial quality control. Most existing UND methods assume that the training data and testing normal data originate from the same domain and only consider the distribution variation between training data and testing data. However, in real scenarios, it is common for normal testing and training data to originate from different domains, a challenge known as domain shift. The discrepancies between training and testing data often lead to incorrect classification of normal data as novel by existing methods. A typical situation is that testing normal data and training data describe the same subject, yet they differ in the background conditions. To address this problem, we introduce a novel method that separates subject information from background variation encapsulating the domain information to enhance detection performance under domain shifts. The proposed method minimizes the mutual information between the representations of the subject and background while modelling the background variation using a deep Gaussian mixture model, where the novelty detection is conducted on the subject representations solely and hence is not affected by the variation of domains. Extensive experiments demonstrate that our model generalizes effectively to unseen domains and significantly outperforms baseline methods, especially under substantial domain shifts between training and testing data.
Authors: Ezra Engel, Lishan Li, Chris Hudy, Robert Schleusner
Abstract: Facial expression recognition (FER) is a subset of computer vision with important applications for human-computer-interaction, healthcare, and customer service. FER represents a challenging problem-space because accurate classification requires a model to differentiate between subtle changes in facial features. In this paper, we examine the use of multi-modal transfer learning to improve performance on a challenging video-based FER dataset, Dynamic Facial Expression in-the-Wild (DFEW). Using a combination of pretrained ResNets, OpenPose, and OmniVec networks, we explore the impact of cross-temporal, multi-modal features on classification accuracy. Ultimately, we find that these finely-tuned multi-modal feature generators modestly improve accuracy of our transformer-based classification model.
Authors: Jinpeng Wang, Tianci Luo, Yaohua Zha, Yan Feng, Ruisheng Luo, Bin Chen, Tao Dai, Long Chen, Yaowei Wang, Shu-Tao Xia
Abstract: Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the existence of a single "ideal" prompt in a pool of candidates, which in practice may not hold true. Multiple suitable prompts may exist, but individually they often fall short, leading to difficulties in selection and the exclusion of useful context. To address this, we propose a new perspective: prompt condensation. Rather than relying on a single prompt, candidate prompts collaborate to efficiently integrate informative contexts without sacrificing resolution. We devise Condenser, a lightweight external plugin that compresses relevant fine-grained context across multiple prompts. Optimized end-to-end with the backbone, Condenser ensures accurate integration of contextual cues. Experiments demonstrate Condenser outperforms state-of-the-arts across benchmark tasks, showing superior context compression, scalability with more prompts, and enhanced computational efficiency compared to ensemble methods, positioning it as a highly competitive solution for VICL. Code is open-sourced at https://github.com/gimpong/CVPR25-Condenser.
Authors: Zhifu Zhao, Hanyang Hua, Jianan Li, Shaoxin Wu, Fu Li, Yangtao Zhou, Yang Li
Abstract: In action recognition tasks, feature diversity is essential for enhancing model generalization and performance. Existing methods typically promote feature diversity by expanding the training data in the sample space, which often leads to inefficiencies and semantic inconsistencies. To overcome these problems, we propose a novel Coarse-fine text co-guidance Diffusion model (CoCoDiff). CoCoDiff generates diverse yet semantically consistent features in the latent space by leveraging diffusion and multi-granularity textual guidance. Specifically, our approach feeds spatio-temporal features extracted from skeleton sequences into a latent diffusion model to generate diverse action representations. Meanwhile, we introduce a coarse-fine text co-guided strategy that leverages textual information from large language models (LLMs) to ensure semantic consistency between the generated features and the original inputs. It is noted that CoCoDiff operates as a plug-and-play auxiliary module during training, incurring no additional inference cost. Extensive experiments demonstrate that CoCoDiff achieves SOTA performance on skeleton-based action recognition benchmarks, including NTU RGB+D, NTU RGB+D 120 and Kinetics-Skeleton.
Authors: Zexin Ji, Beiji Zou, Xiaoyan Kui, Hua Li, Pierre Vera, Su Ruan
Abstract: Multi-modal 3D medical image segmentation aims to accurately identify tumor regions across different modalities, facing challenges from variations in image intensity and tumor morphology. Traditional convolutional neural network (CNN)-based methods struggle with capturing global features, while Transformers-based methods, despite effectively capturing global context, encounter high computational costs in 3D medical image segmentation. The Mamba model combines linear scalability with long-distance modeling, making it a promising approach for visual representation learning. However, Mamba-based 3D multi-modal segmentation still struggles to leverage modality-specific features and fuse complementary information effectively. In this paper, we propose a Mamba based feature extraction and adaptive multilevel feature fusion for 3D tumor segmentation using multi-modal medical image. We first develop the specific modality Mamba encoder to efficiently extract long-range relevant features that represent anatomical and pathological structures present in each modality. Moreover, we design an bi-level synergistic integration block that dynamically merges multi-modal and multi-level complementary features by the modality attention and channel attention learning. Lastly, the decoder combines deep semantic information with fine-grained details to generate the tumor segmentation map. Experimental results on medical image datasets (PET/CT and MRI multi-sequence) show that our approach achieve competitive performance compared to the state-of-the-art CNN, Transformer, and Mamba-based approaches.
Authors: ZiYi Dong, Chengxing Zhou, Weijian Deng, Pengxu Wei, Xiangyang Ji, Liang Lin
Abstract: Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The prevailing paradigm has commonly employed self-attention with quadratic computational complexity to handle global spatial relationships in complex images, thereby synthesizing high-fidelity images with coherent visual semantics.Contrary to conventional wisdom, our systematic layer-wise analysis reveals an interesting discrepancy: self-attention in pre-trained diffusion models predominantly exhibits localized attention patterns, closely resembling convolutional inductive biases. This suggests that global interactions in self-attention may be less critical than commonly assumed.Driven by this, we propose \(\Delta\)ConvFusion to replace conventional self-attention modules with Pyramid Convolution Blocks (\(\Delta\)ConvBlocks).By distilling attention patterns into localized convolutional operations while keeping other components frozen, \(\Delta\)ConvFusion achieves performance comparable to transformer-based counterparts while reducing computational cost by 6929$\times$ and surpassing LinFusion by 5.42$\times$ in efficiency--all without compromising generative fidelity.
Authors: Qianzi Yu, Yang Cao, Yu Kang
Abstract: The latest trend in anomaly detection is to train a unified model instead of training a separate model for each category. However, existing multi-class anomaly detection (MCAD) models perform poorly in multi-view scenarios because they often fail to effectively model the relationships and complementary information among different views. In this paper, we introduce a Multi-View Multi-Class Anomaly Detection model (MVMCAD), which integrates information from multiple views to accurately identify anomalies. Specifically, we propose a semi-frozen encoder, where a pre-encoder prior enhancement mechanism is added before the frozen encoder, enabling stable cross-view feature modeling and efficient adaptation for improved anomaly detection. Furthermore, we propose an Anomaly Amplification Module (AAM) that models global token interactions and suppresses normal regions to enhance anomaly signals, leading to improved detection performance in multi-view settings. Finally, we propose a Cross-Feature Loss that aligns shallow encoder features with deep decoder features and vice versa, enhancing the model's sensitivity to anomalies at different semantic levels under multi-view scenarios. Extensive experiments on the Real-IAD dataset for multi-view multi-class anomaly detection validate the effectiveness of our approach, achieving state-of-the-art performance of 91.0/88.6/82.1 and 99.1/43.9/48.2/95.2 for image-level and the pixel-level, respectively.
Authors: Zhelun Shen, Zhuo Li, Chenming Wu, Zhibo Rao, Lina Liu, Yuchao Dai, Liangjun Zhang
Abstract: Recently, learning-based stereo matching methods have achieved great improvement in public benchmarks, where soft argmin and smooth L1 loss play a core contribution to their success. However, in unsupervised domain adaptation scenarios, we observe that these two operations often yield multimodal disparity probability distributions in target domains, resulting in degraded generalization. In this paper, we propose a novel approach, Constrain Multi-modal Distribution (CMD), to address this issue. Specifically, we introduce \textit{uncertainty-regularized minimization} and \textit{anisotropic soft argmin} to encourage the network to produce predominantly unimodal disparity distributions in the target domain, thereby improving prediction accuracy. Experimentally, we apply the proposed method to multiple representative stereo-matching networks and conduct domain adaptation from synthetic data to unlabeled real-world scenes. Results consistently demonstrate improved generalization in both top-performing and domain-adaptable stereo-matching models. The code for CMD will be available at: \href{https://github.com/gallenszl/CMD}{https://github.com/gallenszl/CMD}.
URLs: https://github.com/gallenszl/CMD, https://github.com/gallenszl/CMD
Authors: Siyi Chen, Yimeng Zhang, Sijia Liu, Qing Qu
Abstract: Despite the remarkable generalization capabilities of diffusion models, recent studies have shown that these models can memorize and generate harmful content when prompted with specific text instructions. Although fine-tuning approaches have been developed to mitigate this issue by unlearning harmful concepts, these methods can be easily circumvented through jailbreaking attacks. This indicates that the harmful concept has not been fully erased from the model. However, existing attack methods, while effective, lack interpretability regarding why unlearned models still retain the concept, thereby hindering the development of defense strategies. In this work, we address these limitations by proposing an attack method that learns an orthogonal set of interpretable attack token embeddings. The attack token embeddings can be decomposed into human-interpretable textual elements, revealing that unlearned models still retain the target concept through implicit textual components. Furthermore, these attack token embeddings are robust and transferable across text prompts, initial noises, and unlearned models. Finally, leveraging this diverse set of embeddings, we design a defense method applicable to both our proposed attack and existing attack methods. Experimental results demonstrate the effectiveness of both our attack and defense strategies.
Authors: Yunhao Li, Sijing Wu, Wei Sun, Zhichao Zhang, Yucheng Zhu, Zicheng Zhang, Huiyu Duan, Xiongkuo Min, Guangtao Zhai
Abstract: The rapid development of text-to-image (T2I) generation approaches has attracted extensive interest in evaluating the quality of generated images, leading to the development of various quality assessment methods for general-purpose T2I outputs. However, existing image quality assessment (IQA) methods are limited to providing global quality scores, failing to deliver fine-grained perceptual evaluations for structurally complex subjects like humans, which is a critical challenge considering the frequent anatomical and textural distortions in AI-generated human images (AGHIs). To address this gap, we introduce AGHI-QA, the first large-scale benchmark specifically designed for quality assessment of AGHIs. The dataset comprises 4,000 images generated from 400 carefully crafted text prompts using 10 state of-the-art T2I models. We conduct a systematic subjective study to collect multidimensional annotations, including perceptual quality scores, text-image correspondence scores, visible and distorted body part labels. Based on AGHI-QA, we evaluate the strengths and weaknesses of current T2I methods in generating human images from multiple dimensions. Furthermore, we propose AGHI-Assessor, a novel quality metric that integrates the large multimodal model (LMM) with domain-specific human features for precise quality prediction and identification of visible and distorted body parts in AGHIs. Extensive experimental results demonstrate that AGHI-Assessor showcases state-of-the-art performance, significantly outperforming existing IQA methods in multidimensional quality assessment and surpassing leading LMMs in detecting structural distortions in AGHIs.
Authors: Modesto Castrill\'on-Santana, Oliverio J Santana, David Freire-Obreg\'on, Daniel Hern\'andez-Sosa, Javier Lorenzo-Navarro
Abstract: Facial expression recognition (FER) is a key research area in computer vision and human-computer interaction. Despite recent advances in deep learning, challenges persist, especially in generalizing to new scenarios. In fact, zero-shot FER significantly reduces the performance of state-of-the-art FER models. To address this problem, the community has recently started to explore the integration of knowledge from Large Language Models for visual tasks. In this work, we evaluate a broad collection of locally executed Visual Language Models (VLMs), avoiding the lack of task-specific knowledge by adopting a Visual Question Answering strategy. We compare the proposed pipeline with state-of-the-art FER models, both integrating and excluding VLMs, evaluating well-known FER benchmarks: AffectNet, FERPlus, and RAF-DB. The results show excellent performance for some VLMs in zero-shot FER scenarios, indicating the need for further exploration to improve FER generalization.
Authors: Abdul Sami, Avinash Kumar, Irfanullah Memon, Youngwon Jo, Muhammad Rizwan, Jaeyoung Choi
Abstract: Automatic font generation (AFG) is the process of creating a new font using only a few examples of the style images. Generating fonts for complex languages like Korean and Chinese, particularly in handwritten styles, presents significant challenges. Traditional AFGs, like Generative adversarial networks (GANs) and Variational Auto-Encoders (VAEs), are usually unstable during training and often face mode collapse problems. They also struggle to capture fine details within font images. To address these problems, we present a diffusion-based AFG method which generates high-quality, diverse Korean font images using only a single reference image, focusing on handwritten and printed styles. Our approach refines noisy images incrementally, ensuring stable training and visually appealing results. A key innovation is our text encoder, which processes phonetic representations to generate accurate and contextually correct characters, even for unseen characters. We used a pre-trained style encoder from DG FONT to effectively and accurately encode the style images. To further enhance the generation quality, we used perceptual loss that guides the model to focus on the global style of generated images. Experimental results on over 2000 Korean characters demonstrate that our model consistently generates accurate and detailed font images and outperforms benchmark methods, making it a reliable tool for generating authentic Korean fonts across different styles.
Authors: Misora Sugiyama, Hirokatsu Kataoka
Abstract: The December 2024 release of OpenAI's Sora, a powerful video generation model driven by natural language prompts, highlights a growing convergence between large language models (LLMs) and video synthesis. As these multimodal systems evolve into video-enabled LLMs (VidLLMs), capable of interpreting, generating, and interacting with visual content, understanding their limitations and ensuring their safe deployment becomes essential. This study investigates visual artifacts frequently found and reported in Sora-generated videos, which can compromise quality, mislead viewers, or propagate disinformation. We propose a multi-label classification framework targeting four common artifact label types: label 1: boundary / edge defects, label 2: texture / noise issues, label 3: movement / joint anomalies, and label 4: object mismatches / disappearances. Using a dataset of 300 manually annotated frames extracted from 15 Sora-generated videos, we trained multiple 2D CNN architectures (ResNet-50, EfficientNet-B3 / B4, ViT-Base). The best-performing model trained by ResNet-50 achieved an average multi-label classification accuracy of 94.14%. This work supports the broader development of VidLLMs by contributing to (1) the creation of datasets for video quality evaluation, (2) interpretable artifact-based analysis beyond language metrics, and (3) the identification of visual risks relevant to factuality and safety.
Authors: Linshan Wu, Yuxiang Nie, Sunan He, Jiaxin Zhuang, Hao Chen
Abstract: Multi-modal interpretation of biomedical images opens up novel opportunities in biomedical image analysis. Conventional AI approaches typically rely on disjointed training, i.e., Large Language Models (LLMs) for clinical text generation and segmentation models for target extraction, which results in inflexible real-world deployment and a failure to leverage holistic biomedical information. To this end, we introduce UniBiomed, the first universal foundation model for grounded biomedical image interpretation. UniBiomed is based on a novel integration of Multi-modal Large Language Model (MLLM) and Segment Anything Model (SAM), which effectively unifies the generation of clinical texts and the segmentation of corresponding biomedical objects for grounded interpretation. In this way, UniBiomed is capable of tackling a wide range of biomedical tasks across ten diverse biomedical imaging modalities. To develop UniBiomed, we curate a large-scale dataset comprising over 27 million triplets of images, annotations, and text descriptions across ten imaging modalities. Extensive validation on 84 internal and external datasets demonstrated that UniBiomed achieves state-of-the-art performance in segmentation, disease recognition, region-aware diagnosis, visual question answering, and report generation. Moreover, unlike previous models that rely on clinical experts to pre-diagnose images and manually craft precise textual or visual prompts, UniBiomed can provide automated and end-to-end grounded interpretation for biomedical image analysis. This represents a novel paradigm shift in clinical workflows, which will significantly improve diagnostic efficiency. In summary, UniBiomed represents a novel breakthrough in biomedical AI, unlocking powerful grounded interpretation capabilities for more accurate and efficient biomedical image analysis.
Authors: Khoa Tuan Nguyen, Ho-min Park, Gaeun Oh, Joris Vankerschaver, Wesley De Neve
Abstract: We propose a novel approach to cervical cell image classification for cervical cancer screening using the EVA-02 transformer model. We developed a four-step pipeline: fine-tuning EVA-02, feature extraction, selecting important features through multiple machine learning models, and training a new artificial neural network with optional loss weighting for improved generalization. With this design, our best model achieved an F1-score of 0.85227, outperforming the baseline EVA-02 model (0.84878). We also utilized Kernel SHAP analysis and identified key features correlating with cell morphology and staining characteristics, providing interpretable insights into the decision-making process of the fine-tuned model. Our code is available at https://github.com/Khoa-NT/isbi2025_ps3c.
Authors: Luoting Zhuang, Seyed Mohammad Hossein Tabatabaei, Ramin Salehi-Rad, Linh M. Tran, Denise R. Aberle, Ashley E. Prosper, William Hsu
Abstract: Objective: A number of machine learning models have utilized semantic features, deep features, or both to assess lung nodule malignancy. However, their reliance on manual annotation during inference, limited interpretability, and sensitivity to imaging variations hinder their application in real-world clinical settings. Thus, this research aims to integrate semantic features derived from radiologists' assessments of nodules, allowing the model to learn clinically relevant, robust, and explainable features for predicting lung cancer. Methods: We obtained 938 low-dose CT scans from the National Lung Screening Trial with 1,246 nodules and semantic features. The Lung Image Database Consortium dataset contains 1,018 CT scans, with 2,625 lesions annotated for nodule characteristics. Three external datasets were obtained from UCLA Health, the LUNGx Challenge, and the Duke Lung Cancer Screening. We finetuned a pretrained Contrastive Language-Image Pretraining model with a parameter-efficient fine-tuning approach to align imaging and semantic features and predict the one-year lung cancer diagnosis. Results: We evaluated the performance of the one-year diagnosis of lung cancer with AUROC and AUPRC and compared it to three state-of-the-art models. Our model demonstrated an AUROC of 0.90 and AUPRC of 0.78, outperforming baseline state-of-the-art models on external datasets. Using CLIP, we also obtained predictions on semantic features, such as nodule margin (AUROC: 0.81), nodule consistency (0.81), and pleural attachment (0.84), that can be used to explain model predictions. Conclusion: Our approach accurately classifies lung nodules as benign or malignant, providing explainable outputs, aiding clinicians in comprehending the underlying meaning of model predictions. This approach also prevents the model from learning shortcuts and generalizes across clinical settings.
Authors: Hong Zhang, Zhongjie Duan, Xingjun Wang, Yingda Chen, Yuze Zhao, Yu Zhang
Abstract: Unified multimodal large language models (MLLMs) aim to integrate multimodal understanding and generation abilities through a single framework. Despite their versatility, existing open-source unified models exhibit performance gaps against domain-specific architectures. To bridge this gap, we present Nexus-Gen, a unified model that synergizes the language reasoning capabilities of LLMs with the image synthesis power of diffusion models. To align the embedding space of the LLM and diffusion model, we conduct a dual-phase alignment training process. (1) The autoregressive LLM learns to predict image embeddings conditioned on multimodal inputs, while (2) the vision decoder is trained to reconstruct high-fidelity images from these embeddings. During training the LLM, we identified a critical discrepancy between the autoregressive paradigm's training and inference phases, where error accumulation in continuous embedding space severely degrades generation quality. To avoid this issue, we introduce a prefilled autoregression strategy that prefills input sequence with position-embedded special tokens instead of continuous embeddings. Through dual-phase training, Nexus-Gen has developed the integrated capability to comprehensively address the image understanding, generation and editing tasks. All models, datasets, and codes are published at https://github.com/modelscope/Nexus-Gen.git to facilitate further advancements across the field.
Authors: Pramook Khungurn, Sukit Seripanitkarn, Phonphrm Thawatdamrongkit, Supasorn Suwajanakorn
Abstract: Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with recovering large-scale image structures and low noise levels with recovering details, this configuration can result in low-quality and blurry images. However, it should be possible to improve details while spending fewer steps recovering structures because the latent code should already contain structural information. Based on this insight, we propose a new DAE training method that improves the quality of reconstructed images. We divide training into two phases. In the first phase, the DAE is trained as a vanilla autoencoder by always setting the noise level to the highest, forcing the encoder and decoder to populate the latent code with structural information. In the second phase, we incorporate a noise schedule that spends more time in the low-noise region, allowing the DAE to learn how to perfect the details. Our method results in images that have accurate high-level structures and low-level details while still preserving useful properties of the latent codes.
Authors: Shijun Zhou, Yajing Liu, Chunhui Hao, Zhiyuan Liu, Jiandong Tian
Abstract: Due to the domain gap between real-world and synthetic hazy images, current data-driven dehazing algorithms trained on synthetic datasets perform well on synthetic data but struggle to generalize to real-world scenarios. To address this challenge, we propose \textbf{I}mage \textbf{D}ehazing \textbf{D}iffusion \textbf{M}odels (IDDM), a novel diffusion process that incorporates the atmospheric scattering model into noise diffusion. IDDM aims to use the gradual haze formation process to help the denoising Unet robustly learn the distribution of clear images from the conditional input hazy images. We design a specialized training strategy centered around IDDM. Diffusion models are leveraged to bridge the domain gap from synthetic to real-world, while the atmospheric scattering model provides physical guidance for haze formation. During the forward process, IDDM simultaneously introduces haze and noise into clear images, and then robustly separates them during the sampling process. By training with physics-guided information, IDDM shows the ability of domain generalization, and effectively restores the real-world hazy images despite being trained on synthetic datasets. Extensive experiments demonstrate the effectiveness of our method through both quantitative and qualitative comparisons with state-of-the-art approaches.
Authors: Teodor Boyadzhiev, Gabriele Lagani, Luca Ciampi, Giuseppe Amato, Krassimira Ivanova
Abstract: The integration of computer vision and deep learning is an essential part of documenting and preserving cultural heritage, as well as improving visitor experiences. In recent years, two deep learning paradigms have been established in the field of computer vision: convolutional neural networks and transformer architectures. The present study aims to make a comparative analysis of some representatives of these two techniques of their ability to transfer knowledge from generic dataset, such as ImageNet, to cultural heritage specific tasks. The results of testing examples of the architectures VGG, ResNet, DenseNet, Visual Transformer, Swin Transformer, and PoolFormer, showed that DenseNet is the best in terms of efficiency-computability ratio.
Authors: Yumeng Shi, Quanyu Long, Wenya Wang
Abstract: Video question answering benefits from the rich information available in videos, enabling a wide range of applications. However, the large volume of tokens generated from longer videos presents significant challenges to memory efficiency and model performance. To alleviate this issue, existing works propose to compress video inputs, but usually overlooking the varying importance of static and dynamic information across different queries, leading to inefficient token usage within limited budgets. To tackle this, we propose a novel token selection strategy, EXPLORE-THEN-SELECT, that adaptively adjust static and dynamic information needed based on question requirements. Our framework first explores different token allocations between static frames, which preserve spatial details, and dynamic frames, which capture temporal changes. Next, it employs a query-aware attention-based metric to select the optimal token combination without model updates. Our proposed framework is plug-and-play that can be seamlessly integrated within diverse video-language models. Extensive experiments show that our method achieves significant performance improvements (up to 5.8%) among various video question answering benchmarks.
Authors: Qi Fan, Kaiqi Liu, Nian Liu, Hisham Cholakkal, Rao Muhammad Anwer, Wenbin Li, Yang Gao
Abstract: Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes in new domains, which is often challenging due to the diverse characteristics of target domains and the limited availability of support data. Most CD-FSS methods redesign and retrain in-domain FSS models using various domain-generalization techniques, which are effective but costly to train. To address these issues, we propose adapting informative model structures of the well-trained FSS model for target domains by learning domain characteristics from few-shot labeled support samples during inference, thereby eliminating the need for retraining. Specifically, we first adaptively identify domain-specific model structures by measuring parameter importance using a novel structure Fisher score in a data-dependent manner. Then, we progressively train the selected informative model structures with hierarchically constructed training samples, progressing from fewer to more support shots. The resulting Informative Structure Adaptation (ISA) method effectively addresses domain shifts and equips existing well-trained in-domain FSS models with flexible adaptation capabilities for new domains, eliminating the need to redesign or retrain CD-FSS models on base data. Extensive experiments validate the effectiveness of our method, demonstrating superior performance across multiple CD-FSS benchmarks.
Authors: Weicai Yan, Wang Lin, Zirun Guo, Ye Wang, Fangming Feng, Xiaoda Yang, Zehan Wang, Tao Jin
Abstract: Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods directly optimize the parameters involved in the prompt generation process through loss backpropagation, which constrains the richness and specificity of the prompt representations. In this paper, we propose Diffusion-Driven Prompt Generator (Diff-Prompt), aiming to use the diffusion model to generate rich and fine-grained prompt information for complex downstream tasks. Specifically, our approach consists of three stages. In the first stage, we train a Mask-VAE to compress the masks into latent space. In the second stage, we leverage an improved Diffusion Transformer (DiT) to train a prompt generator in the latent space, using the masks for supervision. In the third stage, we align the denoising process of the prompt generator with the pre-trained model in the semantic space, and use the generated prompts to fine-tune the model. We conduct experiments on a complex pixel-level downstream task, referring expression comprehension, and compare our method with various parameter-efficient fine-tuning approaches. Diff-Prompt achieves a maximum improvement of 8.87 in R@1 and 14.05 in R@5 compared to the foundation model and also outperforms other state-of-the-art methods across multiple metrics. The experimental results validate the effectiveness of our approach and highlight the potential of using generative models for prompt generation. Code is available at https://github.com/Kelvin-ywc/diff-prompt.
Authors: Chenkai Zhang, Yiming Lei, Zeming Liu, Haitao Leng, ShaoGuo Liu, Tingting Gao, Qingjie Liu, Yunhong Wang
Abstract: With the rapid development of Multi-modal Large Language Models (MLLMs), an increasing number of benchmarks have been established to evaluate the video understanding capabilities of these models. However, these benchmarks focus on \textbf{standalone} videos and mainly assess ``visual elements'' like human actions and object states. In reality, contemporary videos often encompass complex and continuous narratives, typically presented as a \textbf{series}. To address this challenge, we propose \textbf{SeriesBench}, a benchmark consisting of 105 carefully curated narrative-driven series, covering 28 specialized tasks that require deep narrative understanding. Specifically, we first select a diverse set of drama series spanning various genres. Then, we introduce a novel long-span narrative annotation method, combined with a full-information transformation approach to convert manual annotations into diverse task formats. To further enhance model capacity for detailed analysis of plot structures and character relationships within series, we propose a novel narrative reasoning framework, \textbf{PC-DCoT}. Extensive results on \textbf{SeriesBench} indicate that existing MLLMs still face significant challenges in understanding narrative-driven series, while \textbf{PC-DCoT} enables these MLLMs to achieve performance improvements. Overall, our \textbf{SeriesBench} and \textbf{PC-DCoT} highlight the critical necessity of advancing model capabilities to understand narrative-driven series, guiding the future development of MLLMs. SeriesBench is publicly available at https://github.com/zackhxn/SeriesBench-CVPR2025.
Authors: Haoran Chen, Junyan Lin, Xinhao Chen, Yue Fan, Xin Jin, Hui Su, Jianfeng Dong, Jinlan Fu, Xiaoyu Shen
Abstract: Multimodal large language models (MLLMs) have achieved impressive performance across a wide range of tasks, typically using CLIP-ViT as their visual encoder due to its strong text-image alignment capabilities. While prior studies suggest that different CLIP-ViT layers capture different types of information, with shallower layers focusing on fine visual details and deeper layers aligning more closely with textual semantics, most MLLMs still select visual features based on empirical heuristics rather than systematic analysis. In this work, we propose a Layer-wise Representation Similarity approach to group CLIP-ViT layers with similar behaviors into {shallow, middle, and deep} categories and assess their impact on MLLM performance. Building on this foundation, we revisit the visual layer selection problem in MLLMs at scale, training LLaVA-style models ranging from 1.4B to 7B parameters. Through extensive experiments across 10 datasets and 4 tasks, we find that: (1) deep layers are essential for OCR tasks; (2) shallow and middle layers substantially outperform deep layers on reasoning tasks involving counting, positioning, and object localization; (3) a lightweight fusion of features across shallow, middle, and deep layers consistently outperforms specialized fusion baselines and single-layer selections, achieving gains on 9 out of 10 datasets. Our work offers the first principled study of visual layer selection in MLLMs, laying the groundwork for deeper investigations into visual representation learning for MLLMs.
Authors: Shamim Rahim Refat, Ziyan Shirin Raha, Shuvashis Sarker, Faika Fairuj Preotee, MD. Musfikur Rahman, Tashreef Muhammad, Mohammad Shafiul Islam
Abstract: Diabetic retinopathy is a severe eye condition caused by diabetes where the retinal blood vessels get damaged and can lead to vision loss and blindness if not treated. Early and accurate detection is key to intervention and stopping the disease progressing. For addressing this disease properly, this paper presents a comprehensive approach for automated diabetic retinopathy detection by proposing a new hybrid deep learning model called VR-FuseNet. Diabetic retinopathy is a major eye disease and leading cause of blindness especially among diabetic patients so accurate and efficient automated detection methods are required. To address the limitations of existing methods including dataset imbalance, diversity and generalization issues this paper presents a hybrid dataset created from five publicly available diabetic retinopathy datasets. Essential preprocessing techniques such as SMOTE for class balancing and CLAHE for image enhancement are applied systematically to the dataset to improve the robustness and generalizability of the dataset. The proposed VR-FuseNet model combines the strengths of two state-of-the-art convolutional neural networks, VGG19 which captures fine-grained spatial features and ResNet50V2 which is known for its deep hierarchical feature extraction. This fusion improves the diagnostic performance and achieves an accuracy of 91.824%. The model outperforms individual architectures on all performance metrics demonstrating the effectiveness of hybrid feature extraction in Diabetic Retinopathy classification tasks. To make the proposed model more clinically useful and interpretable this paper incorporates multiple XAI techniques. These techniques generate visual explanations that clearly indicate the retinal features affecting the model's prediction such as microaneurysms, hemorrhages and exudates so that clinicians can interpret and validate.
Authors: Luc Vedrenne, Sylvain Faisan, Denis Fortun
Abstract: Point cloud rigid registration is a fundamental problem in 3D computer vision. In the multiview case, we aim to find a set of 6D poses to align a set of objects. Methods based on pairwise registration rely on a subsequent synchronization algorithm, which makes them poorly scalable with the number of views. Generative approaches overcome this limitation, but are based on Gaussian Mixture Models and use an Expectation-Maximization algorithm. Hence, they are not well suited to handle large transformations. Moreover, most existing methods cannot handle high levels of degradations. In this paper, we introduce POLAR (POint cloud LAtent Registration), a multiview registration method able to efficiently deal with a large number of views, while being robust to a high level of degradations and large initial angles. To achieve this, we transpose the registration problem into the latent space of a pretrained autoencoder, design a loss taking degradations into account, and develop an efficient multistart optimization strategy. Our proposed method significantly outperforms state-of-the-art approaches on synthetic and real data. POLAR is available at github.com/pypolar/polar or as a standalone package which can be installed with pip install polaregistration.
Authors: Yu Guo, Guoqing Chen, Tieyong Zeng, Qiyu Jin, Michael Kwok-Po Ng
Abstract: Recovering hidden structures from incomplete or noisy data remains a pervasive challenge across many fields, particularly where multi-dimensional data representation is essential. Quaternion matrices, with their ability to naturally model multi-dimensional data, offer a promising framework for this problem. This paper introduces the quaternion nuclear norm over the Frobenius norm (QNOF) as a novel nonconvex approximation for the rank of quaternion matrices. QNOF is parameter-free and scale-invariant. Utilizing quaternion singular value decomposition, we prove that solving the QNOF can be simplified to solving the singular value $L_1/L_2$ problem. Additionally, we extend the QNOF to robust quaternion matrix completion, employing the alternating direction multiplier method to derive solutions that guarantee weak convergence under mild conditions. Extensive numerical experiments validate the proposed model's superiority, consistently outperforming state-of-the-art quaternion methods.
Authors: Jingjing Liu, Nian Wu, Xianchao Xiu, Jianhua Zhang
Abstract: Non-negative matrix factorization (NMF) is a popular unsupervised learning approach widely used in image clustering. However, in real-world clustering scenarios, most existing NMF methods are highly sensitive to noise corruption and are unable to effectively leverage limited supervised information. To overcome these drawbacks, we propose a unified non-convex framework with label propagation called robust orthogonal nonnegative matrix factorization (RONMF). This method not only considers the graph Laplacian and label propagation as regularization terms but also introduces a more effective non-convex structure to measure the reconstruction error and imposes orthogonal constraints on the basis matrix to reduce the noise corruption, thereby achieving higher robustness. To solve RONMF, we develop an alternating direction method of multipliers (ADMM)-based optimization algorithm. In particular, all subproblems have closed-form solutions, which ensures its efficiency. Experimental evaluations on eight public image datasets demonstrate that the proposed RONMF outperforms state-of-the-art NMF methods across various standard metrics and shows excellent robustness. The code will be available at https://github.com/slinda-liu.
Authors: Xinyu Li, Qi Yao, Yuanda Wang
Abstract: Garment sewing patterns are fundamental design elements that bridge the gap between design concepts and practical manufacturing. The generative modeling of sewing patterns is crucial for creating diversified garments. However, existing approaches are limited either by reliance on a single input modality or by suboptimal generation efficiency. In this work, we present \textbf{\textit{GarmentDiffusion}}, a new generative model capable of producing centimeter-precise, vectorized 3D sewing patterns from multimodal inputs (text, image, and incomplete sewing pattern). Our method efficiently encodes 3D sewing pattern parameters into compact edge token representations, achieving a sequence length that is $\textbf{10}\times$ shorter than that of the autoregressive SewingGPT in DressCode. By employing a diffusion transformer, we simultaneously denoise all edge tokens along the temporal axis, while maintaining a constant number of denoising steps regardless of dataset-specific edge and panel statistics. With all combination of designs of our model, the sewing pattern generation speed is accelerated by $\textbf{100}\times$ compared to SewingGPT. We achieve new state-of-the-art results on DressCodeData, as well as on the largest sewing pattern dataset, namely GarmentCodeData. The project website is available at https://shenfu-research.github.io/Garment-Diffusion/.
Authors: Zherui Zhang, Changwei Wang, Rongtao Xu, Wenhao Xu, Shibiao Xu, Yu Zhang, Li Guo
Abstract: Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image recognition performance on associated datasets, often neglecting the crucial aspect of the transferability of learned representations. In this paper, we propose Category-Aware Embedding Data-Free Knowledge Distillation (CAE-DFKD), which addresses at the embedding level the limitations of previous rely on image-level methods to improve model generalization but fail when directly applied to DFKD. The superiority and flexibility of CAE-DFKD are extensively evaluated, including: \textit{\textbf{i.)}} Significant efficiency advantages resulting from altering the generator training paradigm; \textit{\textbf{ii.)}} Competitive performance with existing DFKD state-of-the-art methods on image recognition tasks; \textit{\textbf{iii.)}} Remarkable transferability of data-free learned representations demonstrated in downstream tasks.
Authors: Hebaixu Wang, Jing Zhang, Haonan Guo, Di Wang, Jiayi Ma, Bo Du
Abstract: Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals often introduce cumulative errors. Moreover, they struggle to balance the commonality of degradation representations and restoration quality. To address these challenges, we introduce \textbf{DGSolver}, a diffusion generalist solver with universal posterior sampling. We first derive the exact ordinary differential equations for generalist diffusion models and tailor high-order solvers with a queue-based accelerated sampling strategy to improve both accuracy and efficiency. We then integrate universal posterior sampling to better approximate manifold-constrained gradients, yielding a more accurate noise estimation and correcting errors in inverse inference. Extensive experiments show that DGSolver outperforms state-of-the-art methods in restoration accuracy, stability, and scalability, both qualitatively and quantitatively. Code and models will be available at https://github.com/MiliLab/DGSolver.
Authors: Qinfeng Zhu, Yunxi Jiang, Lei Fan
Abstract: We propose a result-level category-specific fusion architecture called ClassWise-CRF. This architecture employs a two-stage process: first, it selects expert networks that perform well in specific categories from a pool of candidate networks using a greedy algorithm; second, it integrates the segmentation predictions of these selected networks by adaptively weighting their contributions based on their segmentation performance in each category. Inspired by Conditional Random Field (CRF), the ClassWise-CRF architecture treats the segmentation predictions from multiple networks as confidence vector fields. It leverages segmentation metrics (such as Intersection over Union) from the validation set as priors and employs an exponential weighting strategy to fuse the category-specific confidence scores predicted by each network. This fusion method dynamically adjusts the weights of each network for different categories, achieving category-specific optimization. Building on this, the architecture further optimizes the fused results using unary and pairwise potentials in CRF to ensure spatial consistency and boundary accuracy. To validate the effectiveness of ClassWise-CRF, we conducted experiments on two remote sensing datasets, LoveDA and Vaihingen, using eight classic and advanced semantic segmentation networks. The results show that the ClassWise-CRF architecture significantly improves segmentation performance: on the LoveDA dataset, the mean Intersection over Union (mIoU) metric increased by 1.00% on the validation set and by 0.68% on the test set; on the Vaihingen dataset, the mIoU improved by 0.87% on the validation set and by 0.91% on the test set. These results fully demonstrate the effectiveness and generality of the ClassWise-CRF architecture in semantic segmentation of remote sensing images. The full code is available at https://github.com/zhuqinfeng1999/ClassWise-CRF.
Authors: Junxi Wang, Jize liu, Na Zhang, Yaxiong Wang
Abstract: This paper focuses to detect the fake news on the short video platforms. While significant research efforts have been devoted to this task with notable progress in recent years, current detection accuracy remains suboptimal due to the rapid evolution of content manipulation and generation technologies. Existing approaches typically employ a cross-modal fusion strategy that directly combines raw video data with metadata inputs before applying a classification layer. However, our empirical observations reveal a critical oversight: manipulated content frequently exhibits inter-modal inconsistencies that could serve as valuable discriminative features, yet remain underutilized in contemporary detection frameworks. Motivated by this insight, we propose a novel detection paradigm that explicitly identifies and leverages cross-modal contradictions as discriminative cues. Our approach consists of two core modules: Cross-modal Consistency Learning (CMCL) and Multi-modal Collaborative Diagnosis (MMCD). CMCL includes Pseudo-label Generation (PLG) and Cross-modal Consistency Diagnosis (CMCD). In PLG, a Multimodal Large Language Model is used to generate pseudo-labels for evaluating cross-modal semantic consistency. Then, CMCD extracts [CLS] tokens and computes cosine loss to quantify cross-modal inconsistencies. MMCD further integrates multimodal features through Multimodal Feature Fusion (MFF) and Probability Scores Fusion (PSF). MFF employs a co-attention mechanism to enhance semantic interactions across different modalities, while a Transformer is utilized for comprehensive feature fusion. Meanwhile, PSF further integrates the fake news probability scores obtained in the previous step. Extensive experiments on established benchmarks (FakeSV and FakeTT) demonstrate our model exhibits outstanding performance in Fake videos detection.
Authors: Mengting Wei, Yante Li, Tuomas Varanka, Yan Jiang, Licai Sun, Guoying Zhao
Abstract: In this paper, we propose a method for video face reenactment that integrates a 3D face parametric model into a latent diffusion framework, aiming to improve shape consistency and motion control in existing video-based face generation approaches. Our approach employs the FLAME (Faces Learned with an Articulated Model and Expressions) model as the 3D face parametric representation, providing a unified framework for modeling face expressions and head pose. This enables precise extraction of detailed face geometry and motion features from driving videos. Specifically, we enhance the latent diffusion model with rich 3D expression and detailed pose information by incorporating depth maps, normal maps, and rendering maps derived from FLAME sequences. A multi-layer face movements fusion module with integrated self-attention mechanisms is used to combine identity and motion latent features within the spatial domain. By utilizing the 3D face parametric model as motion guidance, our method enables parametric alignment of face identity between the reference image and the motion captured from the driving video. Experimental results on benchmark datasets show that our method excels at generating high-quality face animations with precise expression and head pose variation modeling. In addition, it demonstrates strong generalization performance on out-of-domain images. Code is publicly available at https://github.com/weimengting/MagicPortrait.
Authors: Uzair Shah, Marco Agus, Daniya Boges, Vanessa Chiappini, Mahmood Alzubaidi, Jens Schneider, Markus Hadwiger, Pierre J. Magistretti, Mowafa Househ, Corrado Cal{\i}
Abstract: We present SAM4EM, a novel approach for 3D segmentation of complex neural structures in electron microscopy (EM) data by leveraging the Segment Anything Model (SAM) alongside advanced fine-tuning strategies. Our contributions include the development of a prompt-free adapter for SAM using two stage mask decoding to automatically generate prompt embeddings, a dual-stage fine-tuning method based on Low-Rank Adaptation (LoRA) for enhancing segmentation with limited annotated data, and a 3D memory attention mechanism to ensure segmentation consistency across 3D stacks. We further release a unique benchmark dataset for the segmentation of astrocytic processes and synapses. We evaluated our method on challenging neuroscience segmentation benchmarks, specifically targeting mitochondria, glia, and synapses, with significant accuracy improvements over state-of-the-art (SOTA) methods, including recent SAM-based adapters developed for the medical domain and other vision transformer-based approaches. Experimental results indicate that our approach outperforms existing solutions in the segmentation of complex processes like glia and post-synaptic densities. Our code and models are available at https://github.com/Uzshah/SAM4EM.
Authors: Sangmin Woo, Kang Zhou, Yun Zhou, Shuai Wang, Sheng Guan, Haibo Ding, Lin Lee Cheong
Abstract: Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability. Surprisingly, we find that simple object-based visual prompting -- overlaying visual cues (e.g., bounding box, circle) on images -- can significantly mitigate such hallucination; however, different visual prompts (VPs) vary in effectiveness. To address this, we propose Black-Box Visual Prompt Engineering (BBVPE), a framework to identify optimal VPs that enhance LVLM responses without needing access to model internals. Our approach employs a pool of candidate VPs and trains a router model to dynamically select the most effective VP for a given input image. This black-box approach is model-agnostic, making it applicable to both open-source and proprietary LVLMs. Evaluations on benchmarks such as POPE and CHAIR demonstrate that BBVPE effectively reduces object hallucination.
Authors: Pengxiang Li, Zhi Gao, Bofei Zhang, Yapeng Mi, Xiaojian Ma, Chenrui Shi, Tao Yuan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
Abstract: Multimodal agents, which integrate a controller (e.g., a large language model) with external tools, have demonstrated remarkable capabilities in tackling complex tasks. However, existing agents need to collect a large number of expert data for fine-tuning to adapt to new environments. In this paper, we propose an online self-exploration method for multimodal agents, namely SPORT, via step-wise preference optimization to refine the trajectories of agents, which automatically generates tasks and learns from solving the generated tasks, without any expert annotation. SPORT operates through four iterative components: task synthesis, step sampling, step verification, and preference tuning. First, we synthesize multi-modal tasks using language models. Then, we introduce a novel search scheme, where step sampling and step verification are executed alternately to solve each generated task. We employ a verifier to provide AI feedback to construct step-wise preference data. The data is subsequently used to update the controller's policy through preference tuning, producing a SPORT Agent. By interacting with real environments, the SPORT Agent evolves into a more refined and capable system. Evaluation in the GTA and GAIA benchmarks show that the SPORT Agent achieves 6.41\% and 3.64\% improvements, underscoring the generalization and effectiveness introduced by our method. The project page is https://SPORT-Agents.github.io.
Authors: Henry John Krumb, Anirban Mukhopadhyay
Abstract: Wireless Capsule Endoscopy is a non-invasive imaging method for the entire gastrointestinal tract, and is a pain-free alternative to traditional endoscopy. It generates extensive video data that requires significant review time, and localizing the capsule after ingestion is a challenge. Techniques like bleeding detection and depth estimation can help with localization of pathologies, but deep learning models are typically too large to run directly on the capsule. Neural Cellular Automata (NCA) for bleeding segmentation and depth estimation are trained on capsule endoscopic images. For monocular depth estimation, we distill a large foundation model into the lean NCA architecture, by treating the outputs of the foundation model as pseudo ground truth. We then port the trained NCA to the ESP32 microcontroller, enabling efficient image processing on hardware as small as a camera capsule. NCA are more accurate (Dice) than other portable segmentation models, while requiring more than 100x fewer parameters stored in memory than other small-scale models. The visual results of NCA depth estimation look convincing, and in some cases beat the realism and detail of the pseudo ground truth. Runtime optimizations on the ESP32-S3 accelerate the average inference speed significantly, by more than factor 3. With several algorithmic adjustments and distillation, it is possible to eNCApsulate NCA models into microcontrollers that fit into wireless capsule endoscopes. This is the first work that enables reliable bleeding segmentation and depth estimation on a miniaturized device, paving the way for precise diagnosis combined with visual odometry as a means of precise localization of the capsule -- on the capsule.
Authors: Thomas L. Athey, Shashata Sawmya, Nir Shavit
Abstract: As both computer vision models and biomedical datasets grow in size, there is an increasing need for efficient inference algorithms. We utilize cascade detectors to efficiently identify sparse objects in multiresolution images. Given an object's prevalence and a set of detectors at different resolutions with known accuracies, we derive the accuracy, and expected number of classifier calls by a cascade detector. These results generalize across number of dimensions and number of cascade levels. Finally, we compare one- and two-level detectors in fluorescent cell detection, organelle segmentation, and tissue segmentation across various microscopy modalities. We show that the multi-level detector achieves comparable performance in 30-75% less time. Our work is compatible with a variety of computer vision models and data domains.
Authors: Daniel Bogdoll, Rajanikant Patnaik Ananta, Abeyankar Giridharan, Isabel Moore, Gregory Stevens, Henry X. Liu
Abstract: With an ever-increasing availability of data, it has become more and more challenging to select and label appropriate samples for the training of machine learning models. It is especially difficult to detect long-tail classes of interest in large amounts of unlabeled data. This holds especially true for Intelligent Transportation Systems (ITS), where vehicle fleets and roadside perception systems generate an abundance of raw data. While industrial, proprietary data engines for such iterative data selection and model training processes exist, researchers and the open-source community suffer from a lack of an openly available system. We present the Mcity Data Engine, which provides modules for the complete data-based development cycle, beginning at the data acquisition phase and ending at the model deployment stage. The Mcity Data Engine focuses on rare and novel classes through an open-vocabulary data selection process. All code is publicly available on GitHub under an MIT license: https://github.com/mcity/mcity_data_engine
Authors: Liqin Wang, Qianyue Hu, Wei Lu, Xiangyang Luo
Abstract: The success of face recognition (FR) systems has led to serious privacy concerns due to potential unauthorized surveillance and user tracking on social networks. Existing methods for enhancing privacy fail to generate natural face images that can protect facial privacy. In this paper, we propose diffusion-based adversarial identity manipulation (DiffAIM) to generate natural and highly transferable adversarial faces against malicious FR systems. To be specific, we manipulate facial identity within the low-dimensional latent space of a diffusion model. This involves iteratively injecting gradient-based adversarial identity guidance during the reverse diffusion process, progressively steering the generation toward the desired adversarial faces. The guidance is optimized for identity convergence towards a target while promoting semantic divergence from the source, facilitating effective impersonation while maintaining visual naturalness. We further incorporate structure-preserving regularization to preserve facial structure consistency during manipulation. Extensive experiments on both face verification and identification tasks demonstrate that compared with the state-of-the-art, DiffAIM achieves stronger black-box attack transferability while maintaining superior visual quality. We also demonstrate the effectiveness of the proposed approach for commercial FR APIs, including Face++ and Aliyun.
Authors: Haiyang Zhou, Wangbo Yu, Jiawen Guan, Xinhua Cheng, Yonghong Tian, Li Yuan
Abstract: The rapid advancement of diffusion models holds the promise of revolutionizing the application of VR and AR technologies, which typically require scene-level 4D assets for user experience. Nonetheless, existing diffusion models predominantly concentrate on modeling static 3D scenes or object-level dynamics, constraining their capacity to provide truly immersive experiences. To address this issue, we propose HoloTime, a framework that integrates video diffusion models to generate panoramic videos from a single prompt or reference image, along with a 360-degree 4D scene reconstruction method that seamlessly transforms the generated panoramic video into 4D assets, enabling a fully immersive 4D experience for users. Specifically, to tame video diffusion models for generating high-fidelity panoramic videos, we introduce the 360World dataset, the first comprehensive collection of panoramic videos suitable for downstream 4D scene reconstruction tasks. With this curated dataset, we propose Panoramic Animator, a two-stage image-to-video diffusion model that can convert panoramic images into high-quality panoramic videos. Following this, we present Panoramic Space-Time Reconstruction, which leverages a space-time depth estimation method to transform the generated panoramic videos into 4D point clouds, enabling the optimization of a holistic 4D Gaussian Splatting representation to reconstruct spatially and temporally consistent 4D scenes. To validate the efficacy of our method, we conducted a comparative analysis with existing approaches, revealing its superiority in both panoramic video generation and 4D scene reconstruction. This demonstrates our method's capability to create more engaging and realistic immersive environments, thereby enhancing user experiences in VR and AR applications.
Authors: Yan Shu, Weichao Zeng, Fangmin Zhao, Zeyu Chen, Zhenhang Li, Xiaomeng Yang, Yu Zhou, Paolo Rota, Xiang Bai, Lianwen Jin, Xu-Cheng Yin, Nicu Sebe
Abstract: Visual text is a crucial component in both document and scene images, conveying rich semantic information and attracting significant attention in the computer vision community. Beyond traditional tasks such as text detection and recognition, visual text processing has witnessed rapid advancements driven by the emergence of foundation models, including text image reconstruction and text image manipulation. Despite significant progress, challenges remain due to the unique properties that differentiate text from general objects. Effectively capturing and leveraging these distinct textual characteristics is essential for developing robust visual text processing models. In this survey, we present a comprehensive, multi-perspective analysis of recent advancements in visual text processing, focusing on two key questions: (1) What textual features are most suitable for different visual text processing tasks? (2) How can these distinctive text features be effectively incorporated into processing frameworks? Furthermore, we introduce VTPBench, a new benchmark that encompasses a broad range of visual text processing datasets. Leveraging the advanced visual quality assessment capabilities of multimodal large language models (MLLMs), we propose VTPScore, a novel evaluation metric designed to ensure fair and reliable evaluation. Our empirical study with more than 20 specific models reveals substantial room for improvement in the current techniques. Our aim is to establish this work as a fundamental resource that fosters future exploration and innovation in the dynamic field of visual text processing. The relevant repository is available at https://github.com/shuyansy/Visual-Text-Processing-survey.
URLs: https://github.com/shuyansy/Visual-Text-Processing-survey.
Authors: Zihan Zhou, Changrui Dai, Aibo Song, Xiaolin Fang
Abstract: Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while efficient, neglect the value of direct involvement of multiple reference frames for reconstruction and decision-making aspects, especially in complex situations such as occlusion or fast movement. In this paper, we introduce a Dynamic Memory Prediction (DMP) framework that innovatively utilizes multiple reference frames to concisely and directly enhance frame reconstruction. Its core component is a Reference Frame Memory Engine that dynamically selects frames based on object pixel features to improve tracking accuracy. In addition, a Bidirectional Target Prediction Network is built to utilize multiple reference frames to improve the robustness of the model. Through experiments, our algorithm outperforms the state-of-the-art self-supervised techniques on two fine-grained video object tracking tasks: object segmentation and keypoint tracking.
Authors: Abu Mohammed Raisuddin, Jesper Holmblad, Hamed Haghighi, Yuri Poledna, Maikol Funk Drechsler, Valentina Donzella, Eren Erdal Aksoy
Abstract: Sensor degradation poses a significant challenge in autonomous driving. During heavy rainfall, the interference from raindrops can adversely affect the quality of LiDAR point clouds, resulting in, for instance, inaccurate point measurements. This, in turn, can potentially lead to safety concerns if autonomous driving systems are not weather-aware, i.e., if they are unable to discern such changes. In this study, we release a new, large-scale, multi-modal emulated rain dataset, REHEARSE-3D, to promote research advancements in 3D point cloud de-raining. Distinct from the most relevant competitors, our dataset is unique in several respects. First, it is the largest point-wise annotated dataset, and second, it is the only one with high-resolution LiDAR data (LiDAR-256) enriched with 4D Radar point clouds logged in both daytime and nighttime conditions in a controlled weather environment. Furthermore, REHEARSE-3D involves rain-characteristic information, which is of significant value not only for sensor noise modeling but also for analyzing the impact of weather at a point level. Leveraging REHEARSE-3D, we benchmark raindrop detection and removal in fused LiDAR and 4D Radar point clouds. Our comprehensive study further evaluates the performance of various statistical and deep-learning models. Upon publication, the dataset and benchmark models will be made publicly available at: https://sporsho.github.io/REHEARSE3D.
Authors: Saber Mehdipour, Seyed Abolghasem Mirroshandel, Seyed Amirhossein Tabatabaei
Abstract: Detecting plant diseases is a crucial aspect of modern agriculture - it plays a key role in maintaining crop health and increasing overall yield. Traditional approaches, though still valuable, often rely on manual inspection or conventional machine learning techniques, both of which face limitations in scalability and accuracy. Recently, Vision Transformers (ViTs) have emerged as a promising alternative, offering benefits such as improved handling of long-range dependencies and better scalability for visual tasks. This survey explores the application of ViTs in precision agriculture, covering tasks from classification to detection and segmentation. We begin by introducing the foundational architecture of ViTs and discuss their transition from Natural Language Processing (NLP) to computer vision. The discussion includes the concept of inductive bias in traditional models like Convolutional Neural Networks (CNNs), and how ViTs mitigate these biases. We provide a comprehensive review of recent literature, focusing on key methodologies, datasets, and performance metrics. The survey also includes a comparative analysis of CNNs and ViTs, with a look at hybrid models and performance enhancements. Technical challenges - such as data requirements, computational demands, and model interpretability - are addressed alongside potential solutions. Finally, we outline potential research directions and technological advancements that could further support the integration of ViTs in real-world agricultural settings. Our goal with this study is to offer practitioners and researchers a deeper understanding of how ViTs are poised to transform smart and precision agriculture.
Authors: Shiying Li, Xingqun Qi, Bingkun Yang, Chen Weile, Zezhao Tian, Muyi Sun, Qifeng Liu, Man Zhang, Zhenan Sun
Abstract: Generating responsive listener head dynamics with nuanced emotions and expressive reactions is crucial for practical dialogue modeling in various virtual avatar animations. Previous studies mainly focus on the direct short-term production of listener behavior. They overlook the fine-grained control over motion variations and emotional intensity, especially in long-sequence modeling. Moreover, the lack of long-term and large-scale paired speaker-listener corpora including head dynamics and fine-grained multi-modality annotations (e.g., text-based expression descriptions, emotional intensity) also limits the application of dialogue modeling.Therefore, we first newly collect a large-scale multi-turn dataset of 3D dyadic conversation containing more than 1.4M valid frames for multi-modal responsive interaction, dubbed ListenerX. Additionally, we propose VividListener, a novel framework enabling fine-grained, expressive and controllable listener dynamics modeling. This framework leverages multi-modal conditions as guiding principles for fostering coherent interactions between speakers and listeners.Specifically, we design the Responsive Interaction Module (RIM) to adaptively represent the multi-modal interactive embeddings. RIM ensures the listener dynamics achieve fine-grained semantic coordination with textual descriptions and adjustments, while preserving expressive reaction with speaker behavior. Meanwhile, we design the Emotional Intensity Tags (EIT) for emotion intensity editing with multi-modal information integration, applying to both text descriptions and listener motion amplitude.Extensive experiments conducted on our newly collected ListenerX dataset demonstrate that VividListener achieves state-of-the-art performance, realizing expressive and controllable listener dynamics.
Authors: Leonhard Sommer, Olaf D\"unkel, Christian Theobalt, Adam Kortylewski
Abstract: 3D morphable models (3DMMs) are a powerful tool to represent the possible shapes and appearances of an object category. Given a single test image, 3DMMs can be used to solve various tasks, such as predicting the 3D shape, pose, semantic correspondence, and instance segmentation of an object. Unfortunately, 3DMMs are only available for very few object categories that are of particular interest, like faces or human bodies, as they require a demanding 3D data acquisition and category-specific training process. In contrast, we introduce a new method, Common3D, that learns 3DMMs of common objects in a fully self-supervised manner from a collection of object-centric videos. For this purpose, our model represents objects as a learned 3D template mesh and a deformation field that is parameterized as an image-conditioned neural network. Different from prior works, Common3D represents the object appearance with neural features instead of RGB colors, which enables the learning of more generalizable representations through an abstraction from pixel intensities. Importantly, we train the appearance features using a contrastive objective by exploiting the correspondences defined through the deformable template mesh. This leads to higher quality correspondence features compared to related works and a significantly improved model performance at estimating 3D object pose and semantic correspondence. Common3D is the first completely self-supervised method that can solve various vision tasks in a zero-shot manner.
Authors: Bahram Jafrasteh, Wei Peng, Cheng Wan, Yimin Luo, Ehsan Adeli, Qingyu Zhao
Abstract: Generative models enhance neuroimaging through data augmentation, quality improvement, and rare condition studies. Despite advances in realistic synthetic MRIs, evaluations focus on texture and perception, lacking sensitivity to crucial anatomical fidelity. This study proposes a new metric, called WASABI (Wasserstein-Based Anatomical Brain Index), to assess the anatomical realism of synthetic brain MRIs. WASABI leverages \textit{SynthSeg}, a deep learning-based brain parcellation tool, to derive volumetric measures of brain regions in each MRI and uses the multivariate Wasserstein distance to compare distributions between real and synthetic anatomies. Based on controlled experiments on two real datasets and synthetic MRIs from five generative models, WASABI demonstrates higher sensitivity in quantifying anatomical discrepancies compared to traditional image-level metrics, even when synthetic images achieve near-perfect visual quality. Our findings advocate for shifting the evaluation paradigm beyond visual inspection and conventional metrics, emphasizing anatomical fidelity as a crucial benchmark for clinically meaningful brain MRI synthesis. Our code is available at https://github.com/BahramJafrasteh/wasabi-mri.
Authors: Alessia Hu, Regina Beets-Tan, Lishan Cai, Eduardo Pooch
Abstract: Magnetic Resonance Imaging (MRI) plays an important role in identifying clinically significant prostate cancer (csPCa), yet automated methods face challenges such as data imbalance, variable tumor sizes, and a lack of annotated data. This study introduces Anomaly-Driven U-Net (adU-Net), which incorporates anomaly maps derived from biparametric MRI sequences into a deep learning-based segmentation framework to improve csPCa identification. We conduct a comparative analysis of anomaly detection methods and evaluate the integration of anomaly maps into the segmentation pipeline. Anomaly maps, generated using Fixed-Point GAN reconstruction, highlight deviations from normal prostate tissue, guiding the segmentation model to potential cancerous regions. We compare the performance by using the average score, computed as the mean of the AUROC and Average Precision (AP). On the external test set, adU-Net achieves the best average score of 0.618, outperforming the baseline nnU-Net model (0.605). The results demonstrate that incorporating anomaly detection into segmentation improves generalization and performance, particularly with ADC-based anomaly maps, offering a promising direction for automated csPCa identification.
Authors: Franko Hrzic, Mohammadreza Movahhedi, Ophelie Lavoie-Gagne, Ata Kiapour
Abstract: It is well known that machine learning models require a high amount of annotated data to obtain optimal performance. Labelling Computed Tomography (CT) data can be a particularly challenging task due to its volumetric nature and often missing and$/$or incomplete associated meta-data. Even inspecting one CT scan requires additional computer software, or in the case of programming languages $-$ additional programming libraries. This study proposes a simple, yet effective approach based on 2D X-ray-like estimation of 3D CT scans for body region identification. Although body region is commonly associated with the CT scan, it often describes only the focused major body region neglecting other anatomical regions present in the observed CT. In the proposed approach, estimated 2D images were utilized to identify 14 distinct body regions, providing valuable information for constructing a high-quality medical dataset. To evaluate the effectiveness of the proposed method, it was compared against 2.5D, 3D and foundation model (MI2) based approaches. Our approach outperformed the others, where it came on top with statistical significance and F1-Score for the best-performing model EffNet-B0 of 0.980 $\pm$ 0.016 in comparison to the 0.840 $\pm$ 0.114 (2.5D DenseNet-161), 0.854 $\pm$ 0.096 (3D VoxCNN), and 0.852 $\pm$ 0.104 (MI2 foundation model). The utilized dataset comprised three different clinical centers and counted 15,622 CT scans (44,135 labels).
Authors: Yixin Gao, Xiaohan Pan, Xin Li, Zhibo Chen
Abstract: The rapid development of AIGC foundation models has revolutionized the paradigm of image compression, which paves the way for the abandonment of most pixel-level transform and coding, compelling us to ask: why compress what you can generate if the AIGC foundation model is powerful enough to faithfully generate intricate structure and fine-grained details from nothing more than some compact descriptors, i.e., texts, or cues. Fortunately, recent GPT-4o image generation of OpenAI has achieved impressive cross-modality generation, editing, and design capabilities, which motivates us to answer the above question by exploring its potential in image compression fields. In this work, we investigate two typical compression paradigms: textual coding and multimodal coding (i.e., text + extremely low-resolution image), where all/most pixel-level information is generated instead of compressing via the advanced GPT-4o image generation function. The essential challenge lies in how to maintain semantic and structure consistency during the decoding process. To overcome this, we propose a structure raster-scan prompt engineering mechanism to transform the image into textual space, which is compressed as the condition of GPT-4o image generation. Extensive experiments have shown that the combination of our designed structural raster-scan prompts and GPT-4o's image generation function achieved the impressive performance compared with recent multimodal/generative image compression at ultra-low bitrate, further indicating the potential of AIGC generation in image compression fields.
Authors: Anas Anwarul Haq Khan, Utkarsh Verma, Prateek Chanda, Ganesh Ramakrishnan
Abstract: We introduce DEEVISum (Distilled Early Exit Vision language model for Summarization), a lightweight, efficient, and scalable vision language model designed for segment wise video summarization. Leveraging multi modal prompts that combine textual and audio derived signals, DEEVISum incorporates Multi Stage Knowledge Distillation (MSKD) and Early Exit (EE) to strike a balance between performance and efficiency. MSKD offers a 1.33% absolute F1 improvement over baseline distillation (0.5%), while EE reduces inference time by approximately 21% with a 1.3 point drop in F1. Evaluated on the TVSum dataset, our best model PaLI Gemma2 3B + MSKD achieves an F1 score of 61.1, competing the performance of significantly larger models, all while maintaining a lower computational footprint. We publicly release our code and processed dataset to support further research.
Authors: Ipek Oztas, Duygu Ceylan, Aysegul Dundar
Abstract: With the growing success of text or image guided 3D generators, users demand more control over the generation process, appearance stylization being one of them. Given a reference image, this requires adapting the appearance of a generated 3D asset to reflect the visual style of the reference while maintaining visual consistency from multiple viewpoints. To tackle this problem, we draw inspiration from the success of 2D stylization methods that leverage the attention mechanisms in large image generation models to capture and transfer visual style. In particular, we probe if large reconstruction models, commonly used in the context of 3D generation, has a similar capability. We discover that the certain attention blocks in these models capture the appearance specific features. By injecting features from a visual style image to such blocks, we develop a simple yet effective 3D appearance stylization method. Our method does not require training or test time optimization. Through both quantitative and qualitative evaluations, we demonstrate that our approach achieves superior results in terms of 3D appearance stylization, significantly improving efficiency while maintaining high-quality visual outcomes.
Authors: Hadleigh Schwartz, Xiaofeng Yan, Charles J. Carver, Xia Zhou
Abstract: High-profile speech videos are prime targets for falsification, owing to their accessibility and influence. This work proposes Spotlight, a low-overhead and unobtrusive system for protecting live speech videos from visual falsification of speaker identity and lip and facial motion. Unlike predominant falsification detection methods operating in the digital domain, Spotlight creates dynamic physical signatures at the event site and embeds them into all video recordings via imperceptible modulated light. These physical signatures encode semantically-meaningful features unique to the speech event, including the speaker's identity and facial motion, and are cryptographically-secured to prevent spoofing. The signatures can be extracted from any video downstream and validated against the portrayed speech content to check its integrity. Key elements of Spotlight include (1) a framework for generating extremely compact (i.e., 150-bit), pose-invariant speech video features, based on locality-sensitive hashing; and (2) an optical modulation scheme that embeds >200 bps into video while remaining imperceptible both in video and live. Prototype experiments on extensive video datasets show Spotlight achieves AUCs $\geq$ 0.99 and an overall true positive rate of 100% in detecting falsified videos. Further, Spotlight is highly robust across recording conditions, video post-processing techniques, and white-box adversarial attacks on its video feature extraction methodologies.
Authors: Derong Jin (University of Maryland, College Park), Ruohan Gao (University of Maryland, College Park)
Abstract: An immersive acoustic experience enabled by spatial audio is just as crucial as the visual aspect in creating realistic virtual environments. However, existing methods for room impulse response estimation rely either on data-demanding learning-based models or computationally expensive physics-based modeling. In this work, we introduce Audio-Visual Differentiable Room Acoustic Rendering (AV-DAR), a framework that leverages visual cues extracted from multi-view images and acoustic beam tracing for physics-based room acoustic rendering. Experiments across six real-world environments from two datasets demonstrate that our multimodal, physics-based approach is efficient, interpretable, and accurate, significantly outperforming a series of prior methods. Notably, on the Real Acoustic Field dataset, AV-DAR achieves comparable performance to models trained on 10 times more data while delivering relative gains ranging from 16.6% to 50.9% when trained at the same scale.
Authors: Xindi Wu, Hee Seung Hwang, Polina Kirichenko, Olga Russakovsky
Abstract: Multimodal Large Language Models (MLLMs) excel at simple vision-language tasks but struggle when faced with complex tasks that require multiple capabilities, such as simultaneously recognizing objects, counting them, and understanding their spatial relationships. This might be partially the result of the fact that Visual Instruction Tuning (VIT), a critical training step for MLLMs, has traditionally focused on scaling data volume, but not the compositional complexity of training examples. We propose COMPACT (COMPositional Atomic-to-complex visual Capability Tuning), which generates a training dataset explicitly controlling for the compositional complexity of the training examples. The data from COMPACT allows MLLMs to train on combinations of atomic capabilities to learn complex capabilities more efficiently. Across all benchmarks, COMPACT achieves comparable performance to the LLaVA-665k VIT while using less than 10% of its data budget, and even outperforms it on several, especially those involving complex multi-capability tasks. For example, COMPACT achieves substantial 83.3% improvement on MMStar and 94.0% improvement on MM-Vet compared to the full-scale VIT on particularly complex questions that require four or more atomic capabilities. COMPACT offers a scalable, data-efficient, visual compositional tuning recipe to improve on complex visual-language tasks.
Authors: Jiwen Yu, Yiran Qin, Haoxuan Che, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Hao Chen, Xihui Liu
Abstract: Interactive Generative Video (IGV) has emerged as a crucial technology in response to the growing demand for high-quality, interactive video content across various domains. In this paper, we define IGV as a technology that combines generative capabilities to produce diverse high-quality video content with interactive features that enable user engagement through control signals and responsive feedback. We survey the current landscape of IGV applications, focusing on three major domains: 1) gaming, where IGV enables infinite exploration in virtual worlds; 2) embodied AI, where IGV serves as a physics-aware environment synthesizer for training agents in multimodal interaction with dynamically evolving scenes; and 3) autonomous driving, where IGV provides closed-loop simulation capabilities for safety-critical testing and validation. To guide future development, we propose a comprehensive framework that decomposes an ideal IGV system into five essential modules: Generation, Control, Memory, Dynamics, and Intelligence. Furthermore, we systematically analyze the technical challenges and future directions in realizing each component for an ideal IGV system, such as achieving real-time generation, enabling open-domain control, maintaining long-term coherence, simulating accurate physics, and integrating causal reasoning. We believe that this systematic analysis will facilitate future research and development in the field of IGV, ultimately advancing the technology toward more sophisticated and practical applications.
Authors: Qihao Liu, Ju He, Qihang Yu, Liang-Chieh Chen, Alan Yuille
Abstract: In recent years, video generation has seen significant advancements. However, challenges still persist in generating complex motions and interactions. To address these challenges, we introduce ReVision, a plug-and-play framework that explicitly integrates parameterized 3D physical knowledge into a pretrained conditional video generation model, significantly enhancing its ability to generate high-quality videos with complex motion and interactions. Specifically, ReVision consists of three stages. First, a video diffusion model is used to generate a coarse video. Next, we extract a set of 2D and 3D features from the coarse video to construct a 3D object-centric representation, which is then refined by our proposed parameterized physical prior model to produce an accurate 3D motion sequence. Finally, this refined motion sequence is fed back into the same video diffusion model as additional conditioning, enabling the generation of motion-consistent videos, even in scenarios involving complex actions and interactions. We validate the effectiveness of our approach on Stable Video Diffusion, where ReVision significantly improves motion fidelity and coherence. Remarkably, with only 1.5B parameters, it even outperforms a state-of-the-art video generation model with over 13B parameters on complex video generation by a substantial margin. Our results suggest that, by incorporating 3D physical knowledge, even a relatively small video diffusion model can generate complex motions and interactions with greater realism and controllability, offering a promising solution for physically plausible video generation.
Authors: Majid Behravan, Maryam Haghani, Denis Gracanin
Abstract: Traditional 3D modeling requires technical expertise, specialized software, and time-intensive processes, making it inaccessible for many users. Our research aims to lower these barriers by combining generative AI and augmented reality (AR) into a cohesive system that allows users to easily generate, manipulate, and interact with 3D models in real time, directly within AR environments. Utilizing cutting-edge AI models like Shap-E, we address the complex challenges of transforming 2D images into 3D representations in AR environments. Key challenges such as object isolation, handling intricate backgrounds, and achieving seamless user interaction are tackled through advanced object detection methods, such as Mask R-CNN. Evaluation results from 35 participants reveal an overall System Usability Scale (SUS) score of 69.64, with participants who engaged with AR/VR technologies more frequently rating the system significantly higher, at 80.71. This research is particularly relevant for applications in gaming, education, and AR-based e-commerce, offering intuitive, model creation for users without specialized skills.
Authors: Yuhan Xie, Yixi Cai, Yinqiang Zhang, Lei Yang, Jia Pan
Abstract: This research tackles the challenge of real-time active view selection and uncertainty quantification on visual quality for active 3D reconstruction. Visual quality is a critical aspect of 3D reconstruction. Recent advancements such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have notably enhanced the image rendering quality of reconstruction models. Nonetheless, the efficient and effective acquisition of input images for reconstruction-specifically, the selection of the most informative viewpoint-remains an open challenge, which is crucial for active reconstruction. Existing studies have primarily focused on evaluating geometric completeness and exploring unobserved or unknown regions, without direct evaluation of the visual uncertainty within the reconstruction model. To address this gap, this paper introduces a probabilistic model that quantifies visual uncertainty for each Gaussian. Leveraging Shannon Mutual Information, we formulate a criterion, Gaussian Splatting Shannon Mutual Information (GauSS-MI), for real-time assessment of visual mutual information from novel viewpoints, facilitating the selection of next best view. GauSS-MI is implemented within an active reconstruction system integrated with a view and motion planner. Extensive experiments across various simulated and real-world scenes showcase the superior visual quality and reconstruction efficiency performance of the proposed system.
Authors: Natnael Alemayehu
Abstract: This study presents a convolutional neural network (CNN)-based approach for the multi-class classification of brain tumors using magnetic resonance imaging (MRI) scans. We utilize a publicly available dataset containing MRI images categorized into four classes: glioma, meningioma, pituitary tumor, and no tumor. Our primary objective is to build a light weight deep learning model that can automatically classify brain tumor types with high accuracy. To achieve this goal, we incorporate image preprocessing steps, including normalization, data augmentation, and a cropping technique designed to reduce background noise and emphasize relevant regions. The CNN architecture is optimized through hyperparameter tuning using Keras Tuner, enabling systematic exploration of network parameters. To ensure reliable evaluation, we apply 5-fold cross-validation, where each hyperparameter configuration is evaluated across multiple data splits to mitigate overfitting. Experimental results demonstrate that the proposed model achieves a classification accuracy of 98.78%, indicating its potential as a diagnostic aid in clinical settings. The proposed method offers a low-complexity yet effective solution for assisting in early brain tumor diagnosis.
Authors: Omid Halimi Milani, Amanda Nikho, Lauren Mills, Marouane Tliba, Ahmet Enis Cetin, Mohammed H. Elnagar
Abstract: Deep learning models have great potential in medical imaging, including orthodontics and skeletal maturity assessment. However, applying a model to data different from its training set can lead to unreliable predictions that may impact patient care. To address this, we propose a comprehensive verification framework that evaluates model suitability through multiple complementary strategies. First, we introduce a Gradient Attention Map (GAM)-based approach that analyzes attention patterns using Grad-CAM and compares them via similarity metrics such as IoU, Dice Similarity, SSIM, Cosine Similarity, Pearson Correlation, KL Divergence, and Wasserstein Distance. Second, we extend verification to early convolutional feature maps, capturing structural mis-alignments missed by attention alone. Finally, we incorporate an additional garbage class into the classification model to explicitly reject out-of-distribution inputs. Experimental results demonstrate that these combined methods effectively identify unsuitable models and inputs, promoting safer and more reliable deployment of deep learning in medical imaging.
Authors: Alfred Yan, Muhammad Nur Talha Kilic, Gert Nolze, Ankit Agrawal, Alok Choudhary, Roberto dos Reis, Vinayak Dravid
Abstract: The design of novel materials hinges on the understanding of structure-property relationships. However, our capability to synthesize a large number of materials has outpaced the ability and speed needed to characterize them. While the overall chemical constituents can be readily known during synthesis, the structural evolution and characterization of newly synthesized samples remains a bottleneck for the ultimate goal of high throughput nanomaterials discovery. Thus, scalable methods for crystal symmetry determination that can analyze a large volume of material samples within a short time-frame are especially needed. Kikuchi diffraction in the SEM is a promising technique for this due to its sensitivity to dynamical scattering, which may provide information beyond just the seven crystal systems and fourteen Bravais lattices. After diffraction patterns are collected from material samples, deep learning methods may be able to classify the space group symmetries using the patterns as input, which paired with the elemental composition, would help enable the determination of the crystal structure. To investigate the feasibility of this solution, neural networks were trained to predict the space group type of background corrected EBSD patterns. Our networks were first trained and tested on an artificial dataset of EBSD patterns of 5,148 different cubic phases, created through physics-based dynamical simulations. Next, Maximum Classifier Discrepancy, an unsupervised deep learning-based domain adaptation method, was utilized to train neural networks to make predictions for experimental EBSD patterns. We introduce a relabeling scheme, which enables our models to achieve accuracy scores higher than 90% on simulated and experimental data, suggesting that neural networks are capable of making predictions of crystal symmetry from an EBSD pattern.
Authors: In\^es Cardoso Oliveira, Decebal Constantin Mocanu, Luis A. Leiva
Abstract: Diffusion models (DMs) are a powerful type of generative models that have achieved state-of-the-art results in various image synthesis tasks and have shown potential in other domains, such as natural language processing and temporal data modeling. Despite their stable training dynamics and ability to produce diverse high-quality samples, DMs are notorious for requiring significant computational resources, both in the training and inference stages. Previous work has focused mostly on increasing the efficiency of model inference. This paper introduces, for the first time, the paradigm of sparse-to-sparse training to DMs, with the aim of improving both training and inference efficiency. We focus on unconditional generation and train sparse DMs from scratch (Latent Diffusion and ChiroDiff) on six datasets using three different methods (Static-DM, RigL-DM, and MagRan-DM) to study the effect of sparsity in model performance. Our experiments show that sparse DMs are able to match and often outperform their Dense counterparts, while substantially reducing the number of trainable parameters and FLOPs. We also identify safe and effective values to perform sparse-to-sparse training of DMs.
Authors: Pranav Saxena, Nishant Raghuvanshi, Neena Goveas
Abstract: A core challenge in AI-guided autonomy is enabling agents to navigate realistically and effectively in previously unseen environments based on natural language commands. We propose UAV-VLN, a novel end-to-end Vision-Language Navigation (VLN) framework for Unmanned Aerial Vehicles (UAVs) that seamlessly integrates Large Language Models (LLMs) with visual perception to facilitate human-interactive navigation. Our system interprets free-form natural language instructions, grounds them into visual observations, and plans feasible aerial trajectories in diverse environments. UAV-VLN leverages the common-sense reasoning capabilities of LLMs to parse high-level semantic goals, while a vision model detects and localizes semantically relevant objects in the environment. By fusing these modalities, the UAV can reason about spatial relationships, disambiguate references in human instructions, and plan context-aware behaviors with minimal task-specific supervision. To ensure robust and interpretable decision-making, the framework includes a cross-modal grounding mechanism that aligns linguistic intent with visual context. We evaluate UAV-VLN across diverse indoor and outdoor navigation scenarios, demonstrating its ability to generalize to novel instructions and environments with minimal task-specific training. Our results show significant improvements in instruction-following accuracy and trajectory efficiency, highlighting the potential of LLM-driven vision-language interfaces for safe, intuitive, and generalizable UAV autonomy.
Authors: Haifeng Huang, Xinyi Chen, Yilun Chen, Hao Li, Xiaoshen Han, Zehan Wang, Tai Wang, Jiangmiao Pang, Zhou Zhao
Abstract: Recent advancements in robotic manipulation have highlighted the potential of intermediate representations for improving policy generalization. In this work, we explore grounding masks as an effective intermediate representation, balancing two key advantages: (1) effective spatial guidance that specifies target objects and placement areas while also conveying information about object shape and size, and (2) broad generalization potential driven by large-scale vision-language models pretrained on diverse grounding datasets. We introduce RoboGround, a grounding-aware robotic manipulation system that leverages grounding masks as an intermediate representation to guide policy networks in object manipulation tasks. To further explore and enhance generalization, we propose an automated pipeline for generating large-scale, simulated data with a diverse set of objects and instructions. Extensive experiments show the value of our dataset and the effectiveness of grounding masks as intermediate guidance, significantly enhancing the generalization abilities of robot policies.
Authors: Ting Qiao, Yingjia Wang, Xing Liu, Sixing Wu, Jianbing Li, Yiming Li
Abstract: Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data to implant hidden backdoors into the model. The compromised model behaves normally on clean samples but misclassifies backdoored samples into the attacker-specified target class, posing a significant threat to real-world DNN applications. Currently, several empirical defense methods have been proposed to mitigate backdoor attacks, but they are often bypassed by more advanced backdoor techniques. In contrast, certified defenses based on randomized smoothing have shown promise by adding random noise to training and testing samples to counteract backdoor attacks. In this paper, we reveal that existing randomized smoothing defenses implicitly assume that all samples are equidistant from the decision boundary. However, it may not hold in practice, leading to suboptimal certification performance. To address this issue, we propose a sample-specific certified backdoor defense method, termed Cert-SSB. Cert-SSB first employs stochastic gradient ascent to optimize the noise magnitude for each sample, ensuring a sample-specific noise level that is then applied to multiple poisoned training sets to retrain several smoothed models. After that, Cert-SSB aggregates the predictions of multiple smoothed models to generate the final robust prediction. In particular, in this case, existing certification methods become inapplicable since the optimized noise varies across different samples. To conquer this challenge, we introduce a storage-update-based certification method, which dynamically adjusts each sample's certification region to improve certification performance. We conduct extensive experiments on multiple benchmark datasets, demonstrating the effectiveness of our proposed method. Our code is available at https://github.com/NcepuQiaoTing/Cert-SSB.
Authors: Feiyu Lu, Mengyu Chen, Hsiang Hsu, Pranav Deshpande, Cheng Yao Wang, Blair MacIntyre
Abstract: Mixed Reality (MR) could assist users' tasks by continuously integrating virtual content with their view of the physical environment. However, where and how to place these content to best support the users has been a challenging problem due to the dynamic nature of MR experiences. In contrast to prior work that investigates optimization-based methods, we are exploring how reinforcement learning (RL) could assist with continuous 3D content placement that is aware of users' poses and their surrounding environments. Through an initial exploration and preliminary evaluation, our results demonstrate the potential of RL to position content that maximizes the reward for users on the go. We further identify future directions for research that could harness the power of RL for personalized and optimized UI and content placement in MR.
Authors: Ayman A. Ameen, Thomas Richter, Andr\'e Kaup
Abstract: Current learned image compression models typically exhibit high complexity, which demands significant computational resources. To overcome these challenges, we propose an innovative approach that employs hierarchical feature extraction transforms to significantly reduce complexity while preserving bit rate reduction efficiency. Our novel architecture achieves this by using fewer channels for high spatial resolution inputs/feature maps. On the other hand, feature maps with a large number of channels have reduced spatial dimensions, thereby cutting down on computational load without sacrificing performance. This strategy effectively reduces the forward pass complexity from \(1256 \, \text{kMAC/Pixel}\) to just \(270 \, \text{kMAC/Pixel}\). As a result, the reduced complexity model can open the way for learned image compression models to operate efficiently across various devices and pave the way for the development of new architectures in image compression technology.
Authors: Jan Koh\'ut, Michal Hradi\v{s}
Abstract: In many machine learning tasks, a large general dataset and a small specialized dataset are available. In such situations, various domain adaptation methods can be used to adapt a general model to the target dataset. We show that in the case of neural networks trained for handwriting recognition using CTC, simple fine-tuning with data augmentation works surprisingly well in such scenarios and that it is resistant to overfitting even for very small target domain datasets. We evaluated the behavior of fine-tuning with respect to augmentation, training data size, and quality of the pre-trained network, both in writer-dependent and writer-independent settings. On a large real-world dataset, fine-tuning on new writers provided an average relative CER improvement of 25 % for 16 text lines and 50 % for 256 text lines.
Authors: Jan Koh\'ut, Michal Hradi\v{s}, Martin Ki\v{s}\v{s}
Abstract: One of the challenges of handwriting recognition is to transcribe a large number of vastly different writing styles. State-of-the-art approaches do not explicitly use information about the writer's style, which may be limiting overall accuracy due to various ambiguities. We explore models with writer-dependent parameters which take the writer's identity as an additional input. The proposed models can be trained on datasets with partitions likely written by a single author (e.g. single letter, diary, or chronicle). We propose a Writer Style Block (WSB), an adaptive instance normalization layer conditioned on learned embeddings of the partitions. We experimented with various placements and settings of WSB and contrastively pre-trained embeddings. We show that our approach outperforms a baseline with no WSB in a writer-dependent scenario and that it is possible to estimate embeddings for new writers. However, domain adaptation using simple fine-tuning in a writer-independent setting provides superior accuracy at a similar computational cost. The proposed approach should be further investigated in terms of training stability and embedding regularization to overcome such a baseline.
Authors: Zeqing Xia, Bojun Xiong, Zhouhui Lian
Abstract: Font design is of vital importance in the digital content design and modern printing industry. Developing algorithms capable of automatically synthesizing vector fonts can significantly facilitate the font design process. However, existing methods mainly concentrate on raster image generation, and only a few approaches can directly synthesize vector fonts. This paper proposes an end-to-end trainable method, VecFontSDF, to reconstruct and synthesize high-quality vector fonts using signed distance functions (SDFs). Specifically, based on the proposed SDF-based implicit shape representation, VecFontSDF learns to model each glyph as shape primitives enclosed by several parabolic curves, which can be precisely converted to quadratic B\'ezier curves that are widely used in vector font products. In this manner, most image generation methods can be easily extended to synthesize vector fonts. Qualitative and quantitative experiments conducted on a publicly-available dataset demonstrate that our method obtains high-quality results on several tasks, including vector font reconstruction, interpolation, and few-shot vector font synthesis, markedly outperforming the state of the art. Our code and trained models are available at https://xiazeqing.github.io/VecFontSDF.
Authors: Haiwei Wu, Jiantao Zhou, Shile Zhang
Abstract: The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the dissemination of fake news or the creation of fake profiles, however, raises significant concerns regarding the authenticity of images. Though many forensic algorithms have been developed for detecting synthetic images, their performance, especially the generalization capability, is still far from being adequate to cope with the increasing number of synthetic models. In this work, we propose a simple yet very effective synthetic image detection method via a language-guided contrastive learning. Specifically, we augment the training images with carefully-designed textual labels, enabling us to use a joint visual-language contrastive supervision for learning a forensic feature space with better generalization. It is shown that our proposed LanguAge-guided SynThEsis Detection (LASTED) model achieves much improved generalizability to unseen image generation models and delivers promising performance that far exceeds state-of-the-art competitors over four datasets. The code is available at https://github.com/HighwayWu/LASTED.
Authors: Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Abstract: Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data augmentation to create two views of the same instance (i.e., positive pairs) and encourage the model to learn good representations by attracting these views closer in the embedding space without collapsing to the trivial solution. However, data augmentation is limited in representing positive pairs, and the repulsion process between the instances during contrastive learning may discard important features for instances that have similar categories. To address this issue, we propose an approach to identify those images with similar semantic content and treat them as positive instances, thereby reducing the chance of discarding important features during representation learning and increasing the richness of the latent representation. Our approach is generic and could work with any self-supervised instance discrimination frameworks such as MoCo and SimSiam. To evaluate our method, we run experiments on three benchmark datasets: ImageNet, STL-10 and CIFAR-10 with different instance discrimination SSL approaches. The experimental results show that our approach consistently outperforms the baseline methods across all three datasets; for instance, we improve upon the vanilla MoCo-v2 by 4.1% on ImageNet under a linear evaluation protocol over 800 epochs. We also report results on semi-supervised learning, transfer learning on downstream tasks, and object detection.
Authors: Jiaming Zhang, Yutao Cui, Gangshan Wu, Limin Wang
Abstract: Current prevailing Video Object Segmentation methods follow the pipeline of extraction-then-matching, which first extracts features on current and reference frames independently, and then performs dense matching between them. This decoupled pipeline limits information propagation between frames to high-level features, hindering fine-grained details for matching. Furthermore, the pixel-wise matching lacks holistic target understanding, making it prone to disturbance by similar distractors. To address these issues, we propose a unified VOS framework, coined as JointFormer, for jointly modeling feature extraction, correspondence matching, and a compressed memory. The core Joint Modeling Block leverages attention to simultaneously extract and propagate the target information from the reference frame to the current frame and a compressed memory token. This joint scheme enables extensive multi-layer propagation beyond high-level feature space and facilitates robust instance-distinctive feature learning. To incorporate the long-term and holistic target information, we introduce a compressed memory token with a customized online updating mechanism, which aggregates target features and facilitates temporal information propagation in a frame-wise manner, enhancing global modeling consistency. Our JointFormer achieves a new state-of-the-art performance on the DAVIS 2017 val/test-dev (89.7\% and 87.6\%) benchmarks and the YouTube-VOS 2018/2019 val (87.0\% and 87.0\%) benchmarks, outperforming the existing works. To demonstrate the generalizability of our model, it is further evaluated on four new benchmarks with various difficulties, including MOSE for complex scenes, VISOR for egocentric videos, VOST for complex transformations, and LVOS for long-term videos.
Authors: Sen Fang, Chunyu Sui, Yanghao Zhou, Xuedong Zhang, Hongbin Zhong, Yapeng Tian, Chen Chen
Abstract: In this paper, we propose a dual-condition diffusion pre-training model named SignDiff that can generate human sign language speakers from a skeleton pose. SignDiff has a novel Frame Reinforcement Network called FR-Net, similar to dense human pose estimation work, which enhances the correspondence between text lexical symbols and sign language dense pose frames, reduces the occurrence of multiple fingers in the diffusion model. In addition, we propose a new method for American Sign Language Production (ASLP), which can generate ASL skeletal pose videos from text input, integrating two new improved modules and a new loss function to improve the accuracy and quality of sign language skeletal posture and enhance the ability of the model to train on large-scale data. We propose the first baseline for ASL production and report the scores of 17.19 and 12.85 on BLEU-4 on the How2Sign dev/test sets. We evaluated our model on the previous mainstream dataset PHOENIX14T, and the experiments achieved the SOTA results. In addition, our image quality far exceeds all previous results by 10 percentage points in terms of SSIM.
Authors: Sean Anthony Byrne, Virmarie Maquiling, Marcus Nystr\"om, Enkelejda Kasneci, Diederick C. Niehorster
Abstract: Deep learning has bolstered gaze estimation techniques, but real-world deployment has been impeded by inadequate training datasets. This problem is exacerbated by both hardware-induced variations in eye images and inherent biological differences across the recorded participants, leading to both feature and pixel-level variance that hinders the generalizability of models trained on specific datasets. While synthetic datasets can be a solution, their creation is both time and resource-intensive. To address this problem, we present a framework called Light Eyes or "LEyes" which, unlike conventional photorealistic methods, only models key image features required for video-based eye tracking using simple light distributions. LEyes facilitates easy configuration for training neural networks across diverse gaze-estimation tasks. We demonstrate that models trained using LEyes are consistently on-par or outperform other state-of-the-art algorithms in terms of pupil and CR localization across well-known datasets. In addition, a LEyes trained model outperforms the industry standard eye tracker using significantly more cost-effective hardware. Going forward, we are confident that LEyes will revolutionize synthetic data generation for gaze estimation models, and lead to significant improvements of the next generation video-based eye trackers.
Authors: Siamul Karim Khan, Patrick Tinsley, Mahsa Mitcheff, Patrick Flynn, Kevin W. Bowyer, Adam Czajka
Abstract: Synthesis of same-identity biometric iris images, both for existing and non-existing identities while preserving the identity across a wide range of pupil sizes, is complex due to the intricate iris muscle constriction mechanism, requiring a precise model of iris non-linear texture deformations to be embedded into the synthesis pipeline. This paper presents the first method of fully data-driven, identity-preserving, pupil size-varying synthesis of iris images. This approach is capable of synthesizing images of irises with different pupil sizes representing non-existing identities, as well as non-linearly deforming the texture of iris images of existing subjects given the segmentation mask of the target iris image. Iris recognition experiments suggest that the proposed deformation model both preserves the identity when changing the pupil size, and offers better similarity between same-identity iris samples with significant differences in pupil size, compared to state-of-the-art linear and non-linear (bio-mechanical-based) iris deformation models. Two immediate applications of the proposed approach are: (a) synthesis of, or enhancement of the existing biometric datasets for iris recognition, mimicking those acquired with iris sensors, and (b) helping forensic human experts examine iris image pairs with significant differences in pupil dilation. Images considered in this work conform to selected ISO/IEC 29794-6 quality metrics to make them applicable in biometric systems. The source codes and model weights are offered with this paper.
Authors: Siyu Ren, Junhui Hou, Xiaodong Chen, Hongkai Xiong, Wenping Wang
Abstract: Qualifying the discrepancy between 3D geometric models, which could be represented with either point clouds or triangle meshes, is a pivotal issue with board applications. Existing methods mainly focus on directly establishing the correspondence between two models and then aggregating point-wise distance between corresponding points, resulting in them being either inefficient or ineffective. In this paper, we propose DDM, an efficient, effective, robust, and differentiable distance metric for 3D geometry data. Specifically, we construct DDM based on the proposed implicit representation of 3D models, namely directional distance field (DDF), which defines the directional distances of 3D points to a model to capture its local surface geometry. We then transfer the discrepancy between two 3D geometric models as the discrepancy between their DDFs defined on an identical domain, naturally establishing model correspondence. To demonstrate the advantage of our DDM, we explore various distance metric-driven 3D geometric modeling tasks, including template surface fitting, rigid registration, non-rigid registration, scene flow estimation and human pose optimization. Extensive experiments show that our DDM achieves significantly higher accuracy under all tasks. As a generic distance metric, DDM has the potential to advance the field of 3D geometric modeling. The source code is available at https://github.com/rsy6318/DDM.
Authors: Wenrui Fan, Mohammod N. I. Suvon, Shuo Zhou, Xianyuan Liu, Samer Alabed, Venet Osmani, Andrew J. Swift, Chen Chen, Haiping Lu
Abstract: Pathology and anatomy are two essential groups of semantics in medical data. Pathology describes what the diseases are, while anatomy explains where the diseases occur. They describe diseases from different perspectives, providing complementary insights into diseases. Thus, properly understanding these semantics and their relationships can enhance medical vision-language models (VLMs). However, pathology and anatomy semantics are usually entangled in medical data, hindering VLMs from explicitly modeling these semantics and their relationships. To address this challenge, we propose MeDSLIP, a novel Medical Dual-Stream Language-Image Pre-training pipeline, to disentangle pathology and anatomy semantics and model the relationships between them. We introduce a dual-stream mechanism in MeDSLIP to explicitly disentangle medical semantics into pathology-relevant and anatomy-relevant streams and align visual and textual information within each stream. Furthermore, we propose an interaction modeling module with prototypical contrastive learning loss and intra-image contrastive learning loss to regularize the relationships between pathology and anatomy semantics. We apply MeDSLIP to chest X-ray analysis and conduct comprehensive evaluations with four benchmark datasets: NIH CXR14, RSNA Pneumonia, SIIM-ACR Pneumothorax, and COVIDx CXR-4. The results demonstrate MeDSLIP's superior generalizability and transferability across different scenarios. The code is available at https://github.com/Shef-AIRE/MeDSLIP, and the pre-trained model is released at https://huggingface.co/pykale/MeDSLIP.
URLs: https://github.com/Shef-AIRE/MeDSLIP,, https://huggingface.co/pykale/MeDSLIP.
Authors: Nikolaos Sarafianos, Tuur Stuyck, Xiaoyu Xiang, Yilei Li, Jovan Popovic, Rakesh Ranjan
Abstract: We introduce Garment3DGen a new method to synthesize 3D garment assets from a base mesh given a single input image as guidance. Our proposed approach allows users to generate 3D textured clothes based on both real and synthetic images, such as those generated by text prompts. The generated assets can be directly draped and simulated on human bodies. We leverage the recent progress of image-to-3D diffusion methods to generate 3D garment geometries. However, since these geometries cannot be utilized directly for downstream tasks, we propose to use them as pseudo ground-truth and set up a mesh deformation optimization procedure that deforms a base template mesh to match the generated 3D target. Carefully designed losses allow the base mesh to freely deform towards the desired target, yet preserve mesh quality and topology such that they can be simulated. Finally, we generate high-fidelity texture maps that are globally and locally consistent and faithfully capture the input guidance, allowing us to render the generated 3D assets. With Garment3DGen users can generate the simulation-ready 3D garment of their choice without the need of artist intervention. We present a plethora of quantitative and qualitative comparisons on various assets and demonstrate that Garment3DGen unlocks key applications ranging from sketch-to-simulated garments or interacting with the garments in VR. Code is publicly available.
Authors: Sen Fang, Chen Chen, Lei Wang, Ce Zheng, Chunyu Sui, Yapeng Tian
Abstract: In this paper, we propose SignLLM, a multilingual Sign Language Production (SLP) large language model, which includes two novel multilingual SLP modes MLSF and Prompt2LangGloss that allow sign language gestures generation from query texts input and question-style prompts input respectively. Both modes can use a new RL loss based on reinforcement learning and a new RL module named Priority Learning Channel. These RL components can accelerate the training by enhancing the model's capability to sample high-quality data. To train SignLLM, we introduce Prompt2Sign, a comprehensive multilingual sign language dataset, which builds from public data, including American Sign Language (ASL) and seven others. This dataset standardizes information by extracting pose information from sign language videos into a unified compressed format. We extensively evaluate SignLLM, demonstrating that our model achieves state-of-the-art performance on SLP tasks across eight sign languages.
Authors: Phillip Howard, Kathleen C. Fraser, Anahita Bhiwandiwalla, Svetlana Kiritchenko
Abstract: With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on both an input image and a text prompt, enabling a variety of use cases such as visual question answering and multimodal chat. While prior studies have examined the social biases contained in text generated by LLMs, this topic has been relatively unexplored in LVLMs. Examining social biases in LVLMs is particularly challenging due to the confounding contributions of bias induced by information contained across the text and visual modalities. To address this challenging problem, we conduct a large-scale study of text generated by different LVLMs under counterfactual changes to input images, producing over 57 million responses from popular models. Our multi-dimensional bias evaluation framework reveals that social attributes such as perceived race, gender, and physical characteristics depicted in images can significantly influence the generation of toxic content, competency-associated words, harmful stereotypes, and numerical ratings of individuals.
Authors: Ruben Wiersma, Julien Philip, Milo\v{s} Ha\v{s}an, Krishna Mullia, Fujun Luan, Elmar Eisemann, Valentin Deschaintre
Abstract: This paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures. Under uncontrolled illumination and unstructured viewpoints, there is no guarantee that the observations contain enough information to reconstruct the appearance properties of a captured object. We study this ambiguity, or uncertainty, using entropy and accelerate the analysis by using the frequency domain, rather than the domain of incoming and outgoing viewing angles. The result is a method that computes a map of uncertainty over an entire object within a millisecond. We find that the frequency model allows us to recover SVBRDF parameters with competitive performance, that the accelerated entropy computation matches results with a physically-based path tracer, and that there is a positive correlation between error and uncertainty. We then show that the uncertainty map can be applied to improve SVBRDF acquisition using capture guidance, sharing information on the surface, and using a diffusion model to inpaint uncertain regions. Our code is available at https://github.com/rubenwiersma/svbrdf_uncertainty.
Authors: Yumeng Zhang, Shi Gong, Kaixin Xiong, Xiaoqing Ye, Xiaofan Li, Xiao Tan, Fan Wang, Jizhou Huang, Hua Wu, Haifeng Wang
Abstract: World models have attracted increasing attention in autonomous driving for their ability to forecast potential future scenarios. In this paper, we propose BEVWorld, a novel framework that transforms multimodal sensor inputs into a unified and compact Bird's Eye View (BEV) latent space for holistic environment modeling. The proposed world model consists of two main components: a multi-modal tokenizer and a latent BEV sequence diffusion model. The multi-modal tokenizer first encodes heterogeneous sensory data, and its decoder reconstructs the latent BEV tokens into LiDAR and surround-view image observations via ray-casting rendering in a self-supervised manner. This enables joint modeling and bidirectional encoding-decoding of panoramic imagery and point cloud data within a shared spatial representation. On top of this, the latent BEV sequence diffusion model performs temporally consistent forecasting of future scenes, conditioned on high-level action tokens, enabling scene-level reasoning over time. Extensive experiments demonstrate the effectiveness of BEVWorld on autonomous driving benchmarks, showcasing its capability in realistic future scene generation and its benefits for downstream tasks such as perception and motion prediction.
Authors: Joshua Nathaniel Williams, Avi Schwarzschild, Yutong He, J. Zico Kolter
Abstract: Recovering natural language prompts for image generation models, solely based on the generated images is a difficult discrete optimization problem. In this work, we present the first head-to-head comparison of recent discrete optimization techniques for the problem of prompt inversion. We evaluate Greedy Coordinate Gradients (GCG), PEZ , Random Search, AutoDAN and BLIP2's image captioner across various evaluation metrics related to the quality of inverted prompts and the quality of the images generated by the inverted prompts. We find that focusing on the CLIP similarity between the inverted prompts and the ground truth image acts as a poor proxy for the similarity between ground truth image and the image generated by the inverted prompts. While the discrete optimizers effectively minimize their objectives, simply using responses from a well-trained captioner often leads to generated images that more closely resemble those produced by the original prompts.
Authors: Reza Kakavand, Reza Ahmadi, Atousa Parsaei, W. Brent Edwards, Amin Komeili
Abstract: This study evaluates the agreement of marker-based and markerless (OpenCap) motion capture systems in assessing joint kinematics and kinetics during cycling. Markerless systems, such as OpenCap, offer the advantage of capturing natural movements without physical markers, making them more practical for real-world applications. However, the agreement of OpenCap with a marker-based system, particularly in cycling, remains underexplored. Ten participants cycled at varying speeds and resistances while motion data were recorded using both systems. Key metrics, including joint angles, moments, and joint reaction loads, were computed using OpenSim and compared using root mean squared error (RMSE) per trial across participants, Pearson correlation coefficients (r) per trial across participants and repeated measures Bland-Altman to control trials dependency within subject. Results revealed very strong agreement (r GT 0.9) for hip (flexion/extension), knee (flexion/extension), and ankle (dorsiflexion/plantarflexion) joint angles.
Authors: Chengqin Wu, Shuai Yu, Tuyan Luo, Qiuhua Rao, Qingson Hu, Jingxiang Xu, Lijun Zhang
Abstract: Underwater visual imaging is crucial for marine engineering, but it suffers from low contrast, blurriness, and color degradation, which hinders downstream analysis. Existing underwater image enhancement methods often treat the haze and color cast as a unified degradation process, neglecting their inherent independence while overlooking their synergistic relationship. To overcome this limitation, we propose a Vision Transformer (ViT)-based network (referred to as WaterFormer) to improve underwater image quality. WaterFormer contains three major components: a dehazing block (DehazeFormer Block) to capture the self-correlated haze features and extract deep-level features, a Color Restoration Block (CRB) to capture self-correlated color cast features, and a Channel Fusion Block (CFB) that dynamically integrates these decoupled features to achieve comprehensive enhancement. To ensure authenticity, a soft reconstruction layer based on the underwater imaging physics model is included. Further, a Chromatic Consistency Loss and Sobel Color Loss are designed to respectively preserve color fidelity and enhance structural details during network training. Comprehensive experimental results demonstrate that WaterFormer outperforms other state-of-the-art methods in enhancing underwater images.
Authors: Geoffrey Kasenbacher, Felix Ehret, Gerrit Ecke, Sebastian Otte
Abstract: The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been shown to be highly effective for enhancing robustness for image recognition tasks in vision pipelines. To additionally maximize representational sparsity, LCA with hard-thresholding can be applied. While this combination often yields very good solutions satisfying an $\ell_0$ sparsity criterion, it comes with significant drawbacks for practical application: (i) LCA is very inefficient, typically requiring hundreds of optimization cycles for convergence; (ii) the use of hard-thresholding results in a non-convex loss function, which might lead to suboptimal minima. To address these issues, we propose the Locally Competitive Algorithm with State Warm-up via Predictive Priming (WARP-LCA), which leverages a predictor network to provide a suitable initial guess of the LCA state based on the current input. Our approach significantly improves both convergence speed and the quality of solutions, while maintaining and even enhancing the overall strengths of LCA. We demonstrate that WARP-LCA converges faster by orders of magnitude and reaches better minima compared to conventional LCA. Moreover, the learned representations are more sparse and exhibit superior properties in terms of reconstruction and denoising quality as well as robustness when applied in deep recognition pipelines. Furthermore, we apply WARP-LCA to image denoising tasks, showcasing its robustness and practical effectiveness. Our findings confirm that the naive use of LCA with hard-thresholding results in suboptimal minima, whereas initializing LCA with a predictive guess results in better outcomes. This research advances the field of biologically inspired deep learning by providing a novel approach to convolutional sparse coding.
Authors: Xinyu Xu, Huazhen Liu, Tao Zhang, Huilin Xiong, Wenxian Yu
Abstract: Semantic segmentation is an important branch of image processing and computer vision. With the popularity of deep learning, various convolutional neural networks have been proposed for pixel-level classification and segmentation tasks. In practical scenarios, however, imaging angles are often arbitrary, encompassing instances such as water body images from remote sensing and capillary and polyp images in the medical domain, where prior orientation information is typically unavailable to guide these networks to extract more effective features. In this case, learning features from objects with diverse orientation information poses a significant challenge, as the majority of CNN-based semantic segmentation networks lack rotation equivariance to resist the disturbance from orientation information. To address this challenge, this paper first constructs a universal convolution-group framework aimed at more fully utilizing orientation information and equipping the network with rotation equivariance. Subsequently, we mathematically design a padding-based rotation equivariant convolution mode (PreCM), which is not only applicable to multi-scale images and convolutional kernels but can also serve as a replacement component for various types of convolutions, such as dilated convolutions, transposed convolutions, and asymmetric convolution. To quantitatively assess the impact of image rotation in semantic segmentation tasks, we also propose a new evaluation metric, Rotation Difference (RD). The replacement experiments related to six existing semantic segmentation networks on three datasets show that, the average Intersection Over Union (IOU) of their PreCM-based versions respectively improve 6.91%, 10.63%, 4.53%, 5.93%, 7.48%, 8.33% compared to their original versions in terms of random angle rotation. And the average RD values are decreased by 3.58%, 4.56%, 3.47%, 3.66%, 3.47%, 3.43% respectively.
Authors: Li Yu, Zhihui Li, Jimin Xiao, Moncef Gabbouj
Abstract: Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing work overlooks the crucial issue that videos reconstructed by these methods lack high-frequency details. To address this problem, this paper introduces a High-Frequency Enhanced Hybrid Neural Representation Network. Our method focuses on leveraging high-frequency information to improve the synthesis of fine details by the network. Specifically, we design a wavelet high-frequency encoder that incorporates Wavelet Frequency Decomposer (WFD) blocks to generate high-frequency feature embeddings. Next, we design the High-Frequency Feature Modulation (HFM) block, which leverages the extracted high-frequency embeddings to enhance the fitting process of the decoder. Finally, with the refined Harmonic decoder block and a Dynamic Weighted Frequency Loss, we further reduce the potential loss of high-frequency information. Experiments on the Bunny and UVG datasets demonstrate that our method outperforms other methods, showing notable improvements in detail preservation and compression performance.
Authors: Xingxi Yin, Zhi Li, Jingfeng Zhang, Chenglin Li, Yin Zhang
Abstract: Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention map of the object and the new color attribute from the text prompt, text-guided image editing methods may fail to change the color of an object, resulting in a misalignment between the resulting image and the text prompt. In this paper, we conduct an in-depth analysis on the process of text-guided image synthesizing and what semantic information different cross-attention blocks have learned. We observe that the visual representation of an object is determined in the up-block of the diffusion model in the early stage of the denoising process, and color adjustment can be achieved through value matrices alignment in the cross-attention layer. Based on our findings, we propose a straightforward, yet stable, and effective image-guided method to modify the color of an object without requiring any additional fine-tuning or training. Lastly, we present a benchmark dataset called COLORBENCH, the first benchmark to evaluate the performance of color change methods. Extensive experiments validate the effectiveness of our method in object-level color editing and surpass the performance of popular text-guided image editing approaches in both synthesized and real images.
Authors: Chiara Mauri, Ryan Fritz, Jocelyn Mora, Benjamin Billot, Juan Eugenio Iglesias, Koen Van Leemput, Jean Augustinack, Douglas N Greve
Abstract: The claustrum is a band-like gray matter structure located between putamen and insula whose exact functions are still actively researched. Its sheet-like structure makes it barely visible in in vivo Magnetic Resonance Imaging (MRI) scans at typical resolutions and neuroimaging tools for its study, including methods for automatic segmentation, are currently very limited. In this paper, we propose a contrast- and resolution-agnostic method for claustrum segmentation at ultra-high resolution (0.35 mm isotropic); the method is based on the SynthSeg segmentation framework (Billot et al., 2023), which leverages the use of synthetic training intensity images to achieve excellent generalization. In particular, SynthSeg requires only label maps to be trained, since corresponding intensity images are synthesized on the fly with random contrast and resolution. We trained a deep learning network for automatic claustrum segmentation, using claustrum manual labels obtained from 18 ultra-high resolution MRI scans (mostly ex vivo). We demonstrated the method to work on these 18 high resolution cases (Dice score = 0.632, mean surface distance = 0.458 mm, and volumetric similarity = 0.867 using 6-fold Cross Validation (CV)), and also on in vivo T1-weighted MRI scans at typical resolutions (~1 mm isotropic). We also demonstrated that the method is robust in a test-retest setting and when applied to multimodal imaging (T2-weighted, Proton Density and quantitative T1 scans). To the best of our knowledge this is the first accurate method for automatic ultra-high resolution claustrum segmentation, which is robust against changes in contrast and resolution. The method is released at https://github.com/chiara-mauri/claustrum_segmentation and as part of the neuroimaging package Freesurfer (Fischl, 2012).
URLs: https://github.com/chiara-mauri/claustrum_segmentation
Authors: Ashmal Vayani, Dinura Dissanayake, Hasindri Watawana, Noor Ahsan, Nevasini Sasikumar, Omkar Thawakar, Henok Biadglign Ademtew, Yahya Hmaiti, Amandeep Kumar, Kartik Kuckreja, Mykola Maslych, Wafa Al Ghallabi, Mihail Mihaylov, Chao Qin, Abdelrahman M Shaker, Mike Zhang, Mahardika Krisna Ihsani, Amiel Esplana, Monil Gokani, Shachar Mirkin, Harsh Singh, Ashay Srivastava, Endre Hamerlik, Fathinah Asma Izzati, Fadillah Adamsyah Maani, Sebastian Cavada, Jenny Chim, Rohit Gupta, Sanjay Manjunath, Kamila Zhumakhanova, Feno Heriniaina Rabevohitra, Azril Amirudin, Muhammad Ridzuan, Daniya Kareem, Ketan More, Kunyang Li, Pramesh Shakya, Muhammad Saad, Amirpouya Ghasemaghaei, Amirbek Djanibekov, Dilshod Azizov, Branislava Jankovic, Naman Bhatia, Alvaro Cabrera, Johan Obando-Ceron, Olympiah Otieno, Fabian Farestam, Muztoba Rabbani, Sanoojan Baliah, Santosh Sanjeev, Abduragim Shtanchaev, Maheen Fatima, Thao Nguyen, Amrin Kareem, Toluwani Aremu, Nathan Xavier, Amit Bhatkal, Hawau Toyin, Aman Chadha, Hisham Cholakkal, Rao Muhammad Anwer, Michael Felsberg, Jorma Laaksonen, Thamar Solorio, Monojit Choudhury, Ivan Laptev, Mubarak Shah, Salman Khan, Fahad Khan
Abstract: Existing Large Multimodal Models (LMMs) generally focus on only a few regions and languages. As LMMs continue to improve, it is increasingly important to ensure they understand cultural contexts, respect local sensitivities, and support low-resource languages, all while effectively integrating corresponding visual cues. In pursuit of culturally diverse global multimodal models, our proposed All Languages Matter Benchmark (ALM-bench) represents the largest and most comprehensive effort to date for evaluating LMMs across 100 languages. ALM-bench challenges existing models by testing their ability to understand and reason about culturally diverse images paired with text in various languages, including many low-resource languages traditionally underrepresented in LMM research. The benchmark offers a robust and nuanced evaluation framework featuring various question formats, including true/false, multiple choice, and open-ended questions, which are further divided into short and long-answer categories. ALM-bench design ensures a comprehensive assessment of a model's ability to handle varied levels of difficulty in visual and linguistic reasoning. To capture the rich tapestry of global cultures, ALM-bench carefully curates content from 13 distinct cultural aspects, ranging from traditions and rituals to famous personalities and celebrations. Through this, ALM-bench not only provides a rigorous testing ground for state-of-the-art open and closed-source LMMs but also highlights the importance of cultural and linguistic inclusivity, encouraging the development of models that can serve diverse global populations effectively. Our benchmark is publicly available.
Authors: Wataru Shimoda, Naoto Inoue, Daichi Haraguchi, Hayato Mitani, Seiichi Uchida, Kota Yamaguchi
Abstract: While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to retouch erroneous text renderings in the post-processing pipeline. Our approach, called Type-R, identifies typographical errors in the generated image, erases the erroneous text, regenerates text boxes for missing words, and finally corrects typos in the rendered words. Through extensive experiments, we show that Type-R, in combination with the latest text-to-image models such as Stable Diffusion or Flux, achieves the highest text rendering accuracy while maintaining image quality and also outperforms text-focused generation baselines in terms of balancing text accuracy and image quality.
Authors: Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Shangchen Han, Fan Zhang, Linguang Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, Tomas Hodan
Abstract: We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (3.7M+ images) of recordings that feature 19 subjects interacting with 33 diverse rigid objects. In addition to simple pick-up, observe, and put-down actions, the subjects perform actions typical for a kitchen, office, and living room environment. The recordings include multiple synchronized data streams containing egocentric multi-view RGB/monochrome images, eye gaze signal, scene point clouds, and 3D poses of cameras, hands, and objects. The dataset is recorded with two headsets from Meta: Project Aria, which is a research prototype of AI glasses, and Quest 3, a virtual-reality headset that has shipped millions of units. Ground-truth poses were obtained by a motion-capture system using small optical markers attached to hands and objects. Hand annotations are provided in the UmeTrack and MANO formats, and objects are represented by 3D meshes with PBR materials obtained by an in-house scanner. In our experiments, we demonstrate the effectiveness of multi-view egocentric data for three popular tasks: 3D hand tracking, model-based 6DoF object pose estimation, and 3D lifting of unknown in-hand objects. The evaluated multi-view methods, whose benchmarking is uniquely enabled by HOT3D, significantly outperform their single-view counterparts.
Authors: Tianqi Li, Ruobing Zheng, Minghui Yang, Jingdong Chen, Ming Yang
Abstract: Recent advances in diffusion models have endowed talking head synthesis with subtle expressions and vivid head movements, but have also led to slow inference speed and insufficient control over generated results. To address these issues, we propose Ditto, a diffusion-based talking head framework that enables fine-grained controls and real-time inference. Specifically, we utilize an off-the-shelf motion extractor and devise a diffusion transformer to generate representations in a specific motion space. We optimize the model architecture and training strategy to address the issues in generating motion representations, including insufficient disentanglement between motion and identity, and large internal discrepancies within the representation. Besides, we employ diverse conditional signals while establishing a mapping between motion representation and facial semantics, enabling control over the generation process and correction of the results. Moreover, we jointly optimize the holistic framework to enable streaming processing, real-time inference, and low first-frame delay, offering functionalities crucial for interactive applications such as AI assistants. Extensive experimental results demonstrate that Ditto generates compelling talking head videos and exhibits superiority in both controllability and real-time performance.
Authors: Valerio Marsocci, Yuru Jia, Georges Le Bellier, David Kerekes, Liang Zeng, Sebastian Hafner, Sebastian Gerard, Eric Brune, Ritu Yadav, Ali Shibli, Heng Fang, Yifang Ban, Maarten Vergauwen, Nicolas Audebert, Andrea Nascetti
Abstract: Geospatial Foundation Models (GFMs) have emerged as powerful tools for extracting representations from Earth observation data, but their evaluation remains inconsistent and narrow. Existing works often evaluate on suboptimal downstream datasets and tasks, that are often too easy or too narrow, limiting the usefulness of the evaluations to assess the real-world applicability of GFMs. Additionally, there is a distinct lack of diversity in current evaluation protocols, which fail to account for the multiplicity of image resolutions, sensor types, and temporalities, which further complicates the assessment of GFM performance. In particular, most existing benchmarks are geographically biased towards North America and Europe, questioning the global applicability of GFMs. To overcome these challenges, we introduce PANGAEA, a standardized evaluation protocol that covers a diverse set of datasets, tasks, resolutions, sensor modalities, and temporalities. It establishes a robust and widely applicable benchmark for GFMs. We evaluate the most popular GFMs openly available on this benchmark and analyze their performance across several domains. In particular, we compare these models to supervised baselines (e.g. UNet and vanilla ViT), and assess their effectiveness when faced with limited labeled data. Our findings highlight the limitations of GFMs, under different scenarios, showing that they do not consistently outperform supervised models. PANGAEA is designed to be highly extensible, allowing for the seamless inclusion of new datasets, models, and tasks in future research. By releasing the evaluation code and benchmark, we aim to enable other researchers to replicate our experiments and build upon our work, fostering a more principled evaluation protocol for large pre-trained geospatial models. The code is available at https://github.com/VMarsocci/pangaea-bench.
Authors: Hao Cheng, Erjia Xiao, Jiayan Yang, Jiahang Cao, Qiang Zhang, Jize Zhang, Kaidi Xu, Jindong Gu, Renjing Xu
Abstract: Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images containing inappropriate content by simply editing the language modality input. To mitigate this security concern, numerous guarding or defensive strategies have been proposed, with a particular emphasis on safeguarding language modality. However, in practical applications, threats in the vision modality, particularly in tasks involving the editing of real-world images, present heightened security risks as they can easily infringe upon the rights of the image owner. Therefore, this paper employs a method named typographic attack to reveal that various image generation models are also susceptible to threats within the vision modality. Furthermore, we also evaluate the defense performance of various existing methods when facing threats in the vision modality and uncover their ineffectiveness. Finally, we propose the Vision Modal Threats in Image Generation Models (VMT-IGMs) dataset, which would serve as a baseline for evaluating the vision modality vulnerability of various image generation models.
Authors: Shiding Zhu, Wenhui Dong, Jun Song, Yingbo Wang, Yanan Guo, Bo Zheng
Abstract: Recently, there has been growing interest in the capability of multimodal large language models (MLLMs) to process high-resolution images. A common approach currently involves dynamically cropping the original high-resolution image into smaller sub-images, which are then fed into a vision encoder that was pre-trained on lower-resolution images. However, this cropping approach often truncates objects and connected areas in the original image, causing semantic breaks. To address this limitation, we introduce HyViLM, designed to process images of any resolution while retaining the overall context during encoding. Specifically, we: (i) Design a new visual encoder called Hybrid Encoder that not only encodes individual sub-images but also interacts with detailed global visual features, significantly improving the model's ability to encode high-resolution images. (ii) Propose an optimal feature fusion strategy for the dynamic cropping approach, effectively leveraging information from different layers of the vision encoder. Compared with the state-of-the-art MLLMs under the same setting, our HyViLM outperforms existing MLLMs in nine out of ten tasks. Specifically, HyViLM achieves a 9.6% improvement in performance on the TextVQA task and a 6.9% enhancement on the DocVQA task.
Authors: Linyi Jin, Richard Tucker, Zhengqi Li, David Fouhey, Noah Snavely, Aleksander Holynski
Abstract: Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly supervising methods for recovering 3D motion remains challenging due to the fundamental difficulty of obtaining ground truth annotations. We present a system for mining high-quality 4D reconstructions from internet stereoscopic, wide-angle videos. Our system fuses and filters the outputs of camera pose estimation, stereo depth estimation, and temporal tracking methods into high-quality dynamic 3D reconstructions. We use this method to generate large-scale data in the form of world-consistent, pseudo-metric 3D point clouds with long-term motion trajectories. We demonstrate the utility of this data by training a variant of DUSt3R to predict structure and 3D motion from real-world image pairs, showing that training on our reconstructed data enables generalization to diverse real-world scenes. Project page and data at: https://stereo4d.github.io
Authors: Dominik Werner Wolf, Alexander Braun, Markus Ulrich
Abstract: 'A trustworthy representation of uncertainty is desirable and should be considered as a key feature of any machine learning method' (Huellermeier and Waegeman, 2021). This conclusion of Huellermeier et al. underpins the importance of calibrated uncertainties. Since AI-based algorithms are heavily impacted by dataset shifts, the automotive industry needs to safeguard its system against all possible contingencies. One important but often neglected dataset shift is caused by optical aberrations induced by the windshield. For the verification of the perception system performance, requirements on the AI performance need to be translated into optical metrics by a bijective mapping. Given this bijective mapping it is evident that the optical system characteristics add additional information about the magnitude of the dataset shift. As a consequence, we propose to incorporate a physical inductive bias into the neural network calibration architecture to enhance the robustness and the trustworthiness of the AI target application, which we demonstrate by using a semantic segmentation task as an example. By utilizing the Zernike coefficient vector of the optical system as a physical prior we can significantly reduce the mean expected calibration error in case of optical aberrations. As a result, we pave the way for a trustworthy uncertainty representation and for a holistic verification strategy of the perception chain.
Authors: Elhoucine Elfatimi, Lahcen El Fatimi, Hanifa Bouchaneb
Abstract: Model checking, a formal verification technique, ensures systems meet predefined requirements, playing a crucial role in minimizing errors and enhancing quality during development. This paper introduces a novel hybrid framework integrating model checking with deep learning for brain tumor detection and validation in medical imaging. By combining model-checking principles with CNN-based feature extraction and K-FCM clustering for segmentation, the proposed approach enhances the reliability of tumor detection and segmentation. Experimental results highlight the framework's effectiveness, achieving 98\% accuracy, 96.15\% precision, and 100\% recall, demonstrating its potential as a robust tool for advanced medical image analysis.
Authors: Dongzhihan Wang, Yang Yang, Liang Xu
Abstract: Visual odometry (VO) plays a crucial role in autonomous driving, robotic navigation, and other related tasks by estimating the position and orientation of a camera based on visual input. Significant progress has been made in data-driven VO methods, particularly those leveraging deep learning techniques to extract image features and estimate camera poses. However, these methods often struggle in low-light conditions because of the reduced visibility of features and the increased difficulty of matching keypoints. To address this limitation, we introduce BrightVO, a novel VO model based on Transformer architecture, which not only performs front-end visual feature extraction, but also incorporates a multi-modality refinement module in the back-end that integrates Inertial Measurement Unit (IMU) data. Using pose graph optimization, this module iteratively refines pose estimates to reduce errors and improve both accuracy and robustness. Furthermore, we create a synthetic low-light dataset, KiC4R, which includes a variety of lighting conditions to facilitate the training and evaluation of VO frameworks in challenging environments. Experimental results demonstrate that BrightVO achieves state-of-the-art performance on both the KiC4R dataset and the KITTI benchmarks. Specifically, it provides an average improvement of 20% in pose estimation accuracy in normal outdoor environments and 259% in low-light conditions, outperforming existing methods. For widespread use and further development, the research work is fully open-source at https://github.com/Anastasiawd/BrightVO.
Authors: Quan Zhang, Yuxin Qi, Xi Tang, Rui Yuan, Xi Lin, Ke Zhang, Chun Yuan
Abstract: Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks.
Authors: Younggun Kim, Beomsik Cho, Seonghoon Ryoo, Soomok Lee
Abstract: Point cloud representation has recently become a research hotspot in the field of computer vision and has been utilized for autonomous vehicles. However, adapting deep learning networks for point cloud data recognition is challenging due to the variability in datasets and sensor technologies. This variability underscores the necessity for adaptive techniques to maintain accuracy under different conditions. In this paper, we present the Multi-View Structural Convolution Network (MSCN) designed for domain-invariant point cloud recognition. MSCN comprises Structural Convolution Layers (SCL) that extract local context geometric features from point clouds and Structural Aggregation Layers (SAL) that extract and aggregate both local and overall context features from point clouds. Additionally, our MSCN enhances feature representation robustness by training with unseen domain point clouds derived from source domain point clouds. This method acquires domain-invariant features and exhibits robust, consistent performance across various point cloud datasets, ensuring compatibility with diverse sensor configurations without the need for parameter adjustments. This highlights MSCN's potential to significantly improve the reliability and domain invariant features in different environments. Our code is available at https://github.com/MLMLab/MSCN.
Authors: Zixue Zeng, Xiaoyan Zhao, Matthew Cartier, Tong Yu, Jing Wang, Xin Meng, Zhiyu Sheng, Maryam Satarpour, John M Cormack, Allison Bean, Ryan Nussbaum, Maya Maurer, Emily Landis-Walkenhorst, Dinesh Kumbhare, Kang Kim, Ajay Wasan, Jiantao Pu
Abstract: We introduce a novel segmentation-aware joint training framework called generative reinforcement network (GRN) that integrates segmentation loss feedback to optimize both image generation and segmentation performance in a single stage. An image enhancement technique called segmentation-guided enhancement (SGE) is also developed, where the generator produces images tailored specifically for the segmentation model. Two variants of GRN were also developed, including GRN for sample-efficient learning (GRN-SEL) and GRN for semi-supervised learning (GRN-SSL). GRN's performance was evaluated using a dataset of 69 fully annotated 3D ultrasound scans from 29 subjects. The annotations included six anatomical structures: dermis, superficial fat, superficial fascial membrane (SFM), deep fat, deep fascial membrane (DFM), and muscle. Our results show that GRN-SEL with SGE reduces labeling efforts by up to 70% while achieving a 1.98% improvement in the Dice Similarity Coefficient (DSC) compared to models trained on fully labeled datasets. GRN-SEL alone reduces labeling efforts by 60%, GRN-SSL with SGE decreases labeling requirements by 70%, and GRN-SSL alone by 60%, all while maintaining performance comparable to fully supervised models. These findings suggest the effectiveness of the GRN framework in optimizing segmentation performance with significantly less labeled data, offering a scalable and efficient solution for ultrasound image analysis and reducing the burdens associated with data annotation.
Authors: Sophie Kerga{\ss}ner, Taimoor Tariq, Piotr Didyk
Abstract: The true vision for real-time virtual and augmented reality is reproducing our visual reality in its entirety on immersive displays. To this end, foveated rendering leverages the limitations of spatial acuity in human peripheral vision to allocate computational resources to the fovea while reducing quality in the periphery. Such methods are often derived from studies on the spatial resolution of the human visual system and its ability to perceive blur in the periphery, enabling the potential for high spatial quality in real-time. However, the effects of blur on other visual cues that depend on luminance contrast, such as depth, remain largely unexplored. It is critical to understand this interplay, as accurate depth representation is a fundamental aspect of visual realism. In this paper, we present the first evaluation exploring the effects of foveated rendering on stereoscopic depth perception. We design a psychovisual experiment to quantitatively study the effects of peripheral blur on depth perception. Our analysis demonstrates that stereoscopic acuity remains unaffected (or even improves) by high levels of peripheral blur. Based on our studies, we derive a simple perceptual model that determines the amount of foveation that does not affect stereoacuity. Furthermore, we analyze the model in the context of common foveation practices reported in literature. The findings indicate that foveated rendering does not impact stereoscopic depth perception, and stereoacuity remains unaffected with up to 2x stronger foveation than commonly used. Finally, we conduct a validation experiment and show that our findings hold for complex natural stimuli.
Authors: Quan Zhang, Yuxin Qi, Xi Tang, Jinwei Fang, Xi Lin, Ke Zhang, Chun Yuan
Abstract: Using extensive training data from SA-1B, the Segment Anything Model (SAM) has demonstrated exceptional generalization and zero-shot capabilities, attracting widespread attention in areas such as medical image segmentation and remote sensing image segmentation. However, its performance in the field of image manipulation detection remains largely unexplored and unconfirmed. There are two main challenges in applying SAM to image manipulation detection: a) reliance on manual prompts, and b) the difficulty of single-view information in supporting cross-dataset generalization. To address these challenges, we develops a cross-view prompt learning paradigm called IMDPrompter based on SAM. Benefiting from the design of automated prompts, IMDPrompter no longer relies on manual guidance, enabling automated detection and localization. Additionally, we propose components such as Cross-view Feature Perception, Optimal Prompt Selection, and Cross-View Prompt Consistency, which facilitate cross-view perceptual learning and guide SAM to generate accurate masks. Extensive experimental results from five datasets (CASIA, Columbia, Coverage, IMD2020, and NIST16) validate the effectiveness of our proposed method.
Authors: Kyle Stein, Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities in learning joint representations of visual and textual data, making them powerful tools for tasks such as Compositional Zero-Shot Learning (CZSL). CZSL requires models to generalize to novel combinations of visual primitives-such as attributes and objects-that were not explicitly encountered during training. Recent works in prompting for CZSL have focused on modifying inputs for the text encoder, often using static prompts that do not change across varying visual contexts. However, these approaches struggle to fully capture varying visual contexts, as they focus on text adaptation rather than leveraging visual features for compositional reasoning. To address this, we propose Visual Adaptive Prompting System (VAPS) that leverages a learnable visual prompt repository and similarity-based retrieval mechanism within the framework of VLMs to bridge the gap between semantic and visual features. Our method introduces a dynamic visual prompt repository mechanism that selects the most relevant attribute and object prompts based on the visual features of the image. Our proposed system includes a visual prompt adapter that encourages the model to learn a more generalizable embedding space. Experiments on three CZSL benchmarks, across both closed and open-world scenarios, demonstrate state-of-the-art results.
Authors: Pankaj Choudhury, Yogesh Aggarwal, Prabhanjan Jadhav, Prithwijit Guha, Sukumar Nandi
Abstract: Most existing works in image caption synthesis use computation heavy deep neural networks and generates image descriptions in English language. This often restricts this important assistive tool for widespread use across language and accessibility barriers. This work presents AC-Lite, a computationally efficient model for image captioning in low-resource Assamese language. AC-Lite reduces computational requirements by replacing computation-heavy deep network components with lightweight alternatives. The AC-Lite model is designed through extensive ablation experiments with different image feature extractor networks and language decoders. A combination of ShuffleNetv2x1.5 with GRU based language decoder along with bilinear attention is found to provide the best performance with minimum compute. AC-Lite was observed to achieve an 82.3 CIDEr score on the COCO-AC dataset with 2.45 GFLOPs and 22.87M parameters.
Authors: Shaibal Saha, Lanyu Xu
Abstract: In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which rely on hierarchical feature extraction, ViTs treat images as sequences of patches and leverage self-attention mechanisms. However, their high computational complexity and memory demands pose significant challenges for deployment on resource-constrained edge devices. To address these limitations, extensive research has focused on model compression techniques and hardware-aware acceleration strategies. Nonetheless, a comprehensive review that systematically categorizes these techniques and their trade-offs in accuracy, efficiency, and hardware adaptability for edge deployment remains lacking. This survey bridges this gap by providing a structured analysis of model compression techniques, software tools for inference on edge, and hardware acceleration strategies for ViTs. We discuss their impact on accuracy, efficiency, and hardware adaptability, highlighting key challenges and emerging research directions to advance ViT deployment on edge platforms, including graphics processing units (GPUs), application-specific integrated circuit (ASICs), and field-programmable gate arrays (FPGAs). The goal is to inspire further research with a contemporary guide on optimizing ViTs for efficient deployment on edge devices.
Authors: Zihan Zhou, Changrui Dai, Aibo Song, Xiaolin Fang
Abstract: Self-supervised video correspondence learning depends on the ability to accurately associate pixels between video frames that correspond to the same visual object. However, achieving reliable pixel matching without supervision remains a major challenge. To address this issue, recent research has focused on feature learning techniques that aim to encode unique pixel representations for matching. Despite these advances, existing methods still struggle to achieve exact pixel correspondences and often suffer from false matches, limiting their effectiveness in self-supervised settings. To this end, we explore an efficient self-supervised Video Correspondence Learning framework (MER) that aims to accurately extract object details from unlabeled videos. First, we design a dedicated Motion Enhancement Engine that emphasizes capturing the dynamic motion of objects in videos. In addition, we introduce a flexible sampling strategy for inter-pixel correspondence information (Multi-Cluster Sampler) that enables the model to pay more attention to the pixel changes of important objects in motion. Through experiments, our algorithm outperforms the state-of-the-art competitors on video correspondence learning tasks such as video object segmentation and video object keypoint tracking.
Authors: Ling Yang, Kaixin Zhu, Juanxi Tian, Bohan Zeng, Mingbao Lin, Hongjuan Pei, Wentao Zhang, Shuicheng Yan
Abstract: With the rapid development of 3D reconstruction technology, research in 4D reconstruction is also advancing, existing 4D reconstruction methods can generate high-quality 4D scenes. However, due to the challenges in acquiring multi-view video data, the current 4D reconstruction benchmarks mainly display actions performed in place, such as dancing, within limited scenarios. In practical scenarios, many scenes involve wide-range spatial movements, highlighting the limitations of existing 4D reconstruction datasets. Additionally, existing 4D reconstruction methods rely on deformation fields to estimate the dynamics of 3D objects, but deformation fields struggle with wide-range spatial movements, which limits the ability to achieve high-quality 4D scene reconstruction with wide-range spatial movements. In this paper, we focus on 4D scene reconstruction with significant object spatial movements and propose a novel 4D reconstruction benchmark, WideRange4D. This benchmark includes rich 4D scene data with large spatial variations, allowing for a more comprehensive evaluation of the generation capabilities of 4D generation methods. Furthermore, we introduce a new 4D reconstruction method, Progress4D, which generates stable and high-quality 4D results across various complex 4D scene reconstruction tasks. We conduct both quantitative and qualitative comparison experiments on WideRange4D, showing that our Progress4D outperforms existing state-of-the-art 4D reconstruction methods. Project: https://github.com/Gen-Verse/WideRange4D
Authors: Suzhe Xu, Jialin Peng, Chengyuan Zhang
Abstract: Segmentation is a fundamental task in computer vision, with prompt-driven methods gaining prominence due to their flexibility. The Segment Anything Model (SAM) excels at point-prompted segmentation, while text-based models, often leveraging powerful multimodal encoders like BEIT-3, provide rich semantic understanding. However, effectively combining these complementary modalities remains a challenge. This paper introduces BiPrompt-SAM, a novel dual-modal prompt segmentation framework employing an explicit selection mechanism. We leverage SAM's ability to generate multiple mask candidates from a single point prompt and use a text-guided mask (generated via EVF-SAM with BEIT-3) to select the point-generated mask that best aligns spatially, measured by Intersection over Union (IoU). This approach, interpretable as a simplified Mixture of Experts (MoE), effectively fuses spatial precision and semantic context without complex model modifications. Notably, our method achieves strong zero-shot performance on the Endovis17 medical dataset (89.55% mDice, 81.46% mIoU) using only a single point prompt per instance. This significantly reduces annotation burden compared to bounding boxes and aligns better with practical clinical workflows, demonstrating the method's effectiveness without domain-specific training. On the RefCOCO series, BiPrompt-SAM attained 87.1%, 86.5%, and 85.8% IoU, significantly outperforming existing approaches. Experiments show BiPrompt-SAM excels in scenarios requiring both spatial accuracy and semantic disambiguation, offering a simple, effective, and interpretable perspective on multi-modal prompt fusion.
Authors: Fenglei Hao, Yuliang Yang, Ruiyuan Su, Zhengran Zhao, Yukun Qiao, Mengyu Zhu
Abstract: This paper addresses the challenge of capturing global temporaldependencies in long video sequences for Video Object Segmentation (VOS). Existing architectures often fail to effectively model these dependencies acrossextended temporal horizons. To overcome this limitation, we introduce GISE-TTT, anovel architecture that integrates Temporal Transformer (TTT) layers intotransformer-based frameworks through a co-designed hierarchical approach.The TTTlayer systematically condenses historical temporal information into hidden states thatencode globally coherent contextual representations. By leveraging multi-stagecontextual aggregation through hierarchical concatenation, our frameworkprogressively refines spatiotemporal dependencies across network layers. This designrepresents the first systematic empirical evidence that distributing global informationacross multiple network layers is critical for optimal dependency utilization in videosegmentation tasks.Ablation studies demonstrate that incorporating TTT modules athigh-level feature stages significantly enhances global modeling capabilities, therebyimproving the network's ability to capture long-range temporal relationships. Extensive experiments on DAVIS 2017 show that GISE-TTT achieves a 3.2%improvement in segmentation accuracy over the baseline model, providingcomprehensive evidence that global information should be strategically leveragedthroughout the network architecture.The code will be made available at:https://github.com/uuool/GISE-TTT.
Authors: Huijie Liu, Bingcan Wang, Jie Hu, Xiaoming Wei, Guoliang Kang
Abstract: Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and e-commerce. In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes. To address this limitation, we propose Omni-Dish, the first text-to-image generation model specifically tailored for Chinese dishes. We develop a comprehensive dish curation pipeline, building the largest dish dataset to date. Additionally, we introduce a recaption strategy and employ a coarse-to-fine training scheme to help the model better learn fine-grained culinary nuances. During inference, we enhance the user's textual input using a pre-constructed high-quality caption library and a large language model, enabling more photorealistic and faithful image generation. Furthermore, to extend our model's capability for dish editing tasks, we propose Concept-Enhanced P2P. Based on this approach, we build a dish editing dataset and train a specialized editing model. Extensive experiments demonstrate the superiority of our methods.
Authors: Eunsoo Im, Changhyun Jee, Jung Kwon Lee
Abstract: The emerging trend in computer vision emphasizes developing universal models capable of simultaneously addressing multiple diverse tasks. Such universality typically requires joint training across multi-domain datasets to ensure effective generalization. However, monocular 3D object detection presents unique challenges in multi-domain training due to the scarcity of datasets annotated with accurate 3D ground-truth labels, especially beyond typical road-based autonomous driving contexts. To address this challenge, we introduce a novel weakly supervised framework leveraging pseudo-labels. Current pretrained models often struggle to accurately detect pedestrians in non-road environments due to inherent dataset biases. Unlike generalized image-based 2D object detection models, achieving similar generalization in monocular 3D detection remains largely unexplored. In this paper, we propose GATE3D, a novel framework designed specifically for generalized monocular 3D object detection via weak supervision. GATE3D effectively bridges domain gaps by employing consistency losses between 2D and 3D predictions. Remarkably, our model achieves competitive performance on the KITTI benchmark as well as on an indoor-office dataset collected by us to evaluate the generalization capabilities of our framework. Our results demonstrate that GATE3D significantly accelerates learning from limited annotated data through effective pre-training strategies, highlighting substantial potential for broader impacts in robotics, augmented reality, and virtual reality applications. Project page: https://ies0411.github.io/GATE3D/
Authors: Weijie He, Mushui Liu, Yunlong Yu, Zhao Wang, Chao Wu
Abstract: Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical challenge for diffusion-based models. Existing methods struggle with layout discontinuity, entity identity drift, and implausible interaction dynamics due to unconstrained cross-attention mechanisms and inadequate physics-aware reasoning. To address these limitations, we propose DyST-XL, a \textbf{training-free} framework that enhances off-the-shelf text-to-video models (e.g., CogVideoX-5B) through frame-aware control. DyST-XL integrates three key innovations: (1) A Dynamic Layout Planner that leverages large language models (LLMs) to parse input prompts into entity-attribute graphs and generates physics-aware keyframe layouts, with intermediate frames interpolated via trajectory optimization; (2) A Dual-Prompt Controlled Attention Mechanism that enforces localized text-video alignment through frame-aware attention masking, achieving precise control over individual entities; and (3) An Entity-Consistency Constraint strategy that propagates first-frame feature embeddings to subsequent frames during denoising, preserving object identity without manual annotation. Experiments demonstrate that DyST-XL excels in compositional text-to-video generation, significantly improving performance on complex prompts and bridging a crucial gap in training-free video synthesis. The code is released in https://github.com/XiaoBuL/DyST-XL.
Authors: Minh-Quan Viet Bui, Jongmin Park, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim
Abstract: We present MoBGS, a novel deblurring dynamic 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel view synthesis (NVS) methods are highly sensitive to motion blur in casually captured videos, resulting in significant degradation of rendering quality. While recent approaches address motion-blurred inputs for NVS, they primarily focus on static scene reconstruction and lack dedicated motion modeling for dynamic objects. To overcome these limitations, our MoBGS introduces a novel Blur-adaptive Latent Camera Estimation (BLCE) method for effective latent camera trajectory estimation, improving global camera motion deblurring. In addition, we propose a physically-inspired Latent Camera-induced Exposure Estimation (LCEE) method to ensure consistent deblurring of both global camera and local object motion. Our MoBGS framework ensures the temporal consistency of unseen latent timestamps and robust motion decomposition of static and dynamic regions. Extensive experiments on the Stereo Blur dataset and real-world blurry videos show that our MoBGS significantly outperforms the very recent advanced methods (DyBluRF and Deblur4DGS), achieving state-of-the-art performance for dynamic NVS under motion blur.
Authors: Andr\'e Longon
Abstract: An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic interpretability research has illuminated some invariance-building circuitry in InceptionV1, but the results are limited and networks with different architectures have remained largely unexplored. This work investigates ResNet18 with a particular focus on its residual stream, an architectural component which InceptionV1 lacks. We observe that many convolutional channels in intermediate blocks exhibit scale invariant properties, computed by the element-wise residual summation of scale equivariant representations: the block input's smaller-scale copy with the block pre-sum output's larger-scale copy. Through subsequent ablation experiments, we attempt to causally link these neural properties with scale-robust object recognition behavior. Our tentative findings suggest how the residual stream computes scale invariance and its possible role in behavior. Code is available at: https://github.com/cest-andre/residual-stream-interp
Authors: Giacomo Pacini, Lorenzo Bianchi, Luca Ciampi, Nicola Messina, Giuseppe Amato, Fabrizio Falchi
Abstract: Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods offer flexibility at inference time, they still rely heavily on labeled data for training, which limits scalability and generalization to many downstream use cases. In this paper, we introduce CountingDINO, the first training-free exemplar-based CAC framework that exploits a fully unsupervised feature extractor. Specifically, our approach employs self-supervised vision-only backbones to extract object-aware features, and it eliminates the need for annotated data throughout the entire proposed pipeline. At inference time, we extract latent object prototypes via ROI-Align from DINO features and use them as convolutional kernels to generate similarity maps. These are then transformed into density maps through a simple yet effective normalization scheme. We evaluate our approach on the FSC-147 benchmark, where we consistently outperform a baseline based on an SOTA unsupervised object detector under the same label- and training-free setting. Additionally, we achieve competitive results -- and in some cases surpass -- training-free methods that rely on supervised backbones, non-training-free unsupervised methods, as well as several fully supervised SOTA approaches. This demonstrates that label- and training-free CAC can be both scalable and effective. Code: https://lorebianchi98.github.io/CountingDINO/.
Authors: Shuhao Kang, Martin Y. Liao, Yan Xia, Olaf Wysocki, Boris Jutzi, Daniel Cremers
Abstract: LiDAR place recognition is a critical capability for autonomous navigation and cross-modal localization in large-scale outdoor environments. Existing approaches predominantly depend on pre-built 3D dense maps or aerial imagery, which impose significant storage overhead and lack real-time adaptability. In this paper, we propose OPAL, a novel network for LiDAR place recognition that leverages OpenStreetMap (OSM) as a lightweight and up-to-date prior. Our key innovation lies in bridging the domain disparity between sparse LiDAR scans and structured OSM data through two carefully designed components. First, a cross-modal visibility mask that identifies maximal observable regions from both modalities to guide feature learning. Second, an adaptive radial fusion module that dynamically consolidates radial features into discriminative global descriptors. Extensive experiments on the KITTI and KITTI-360 datasets demonstrate OPAL's superiority, achieving 15.98% higher recall at @1m threshold for top-1 retrieved matches, along with 12x faster inference speed compared to the state-of-the-art approach. Code and datasets will be publicly available.
Authors: Rustam Tagiew (German Centre for Rail Traffic Research at the Federal Railway Authority), Prasannavenkatesh Balaji (German Centre for Rail Traffic Research at the Federal Railway Authority)
Abstract: Points 2.1.4(b), 2.4.2(b) and 2.4.3(b) in Annex I of Implementing Regulation (EU) No. 402/2013 allow a simplified approach for the safety approval of computer vision systems for driverless trains, if they have 'similar' functions and interfaces as the replaced human driver. The human driver is not replaced one-to-one by a technical system - only a limited set of cognitive functions are replaced. However, performance in the most challenging function, obstacle detection, is difficult to quantify due to the deficiency of published measurement results. This article summarizes the data published so far. This article also goes a long way to remedy this situation by providing a new public and anonymized dataset of 711 train driver performance measurements from controlled experiments. The measurements are made for different speeds, obstacle sizes, train protection systems and obstacle color contrasts respectively. The measured values are reaction time and distance to the obstacle. The goal of this paper is an unbiased and exhaustive description of the presented dataset for research, standardization and regulation. The dataset with supplementing information and literature is published on https://data.fid-move.de/de/dataset/atosensedata
Authors: Noriyuki Kugo, Xiang Li, Zixin Li, Ashish Gupta, Arpandeep Khatua, Nidhish Jain, Chaitanya Patel, Yuta Kyuragi, Yasunori Ishii, Masamoto Tanabiki, Kazuki Kozuka, Ehsan Adeli
Abstract: Video Question Answering (VQA) inherently relies on multimodal reasoning, integrating visual, temporal, and linguistic cues to achieve a deeper understanding of video content. However, many existing methods rely on feeding frame-level captions into a single model, making it difficult to adequately capture temporal and interactive contexts. To address this limitation, we introduce VideoMultiAgents, a framework that integrates specialized agents for vision, scene graph analysis, and text processing. It enhances video understanding leveraging complementary multimodal reasoning from independently operating agents. Our approach is also supplemented with a question-guided caption generation, which produces captions that highlight objects, actions, and temporal transitions directly relevant to a given query, thus improving the answer accuracy. Experimental results demonstrate that our method achieves state-of-the-art performance on Intent-QA (79.0%, +6.2% over previous SOTA), EgoSchema subset (75.4%, +3.4%), and NExT-QA (79.6%, +0.4%). The source code is available at https://github.com/PanasonicConnect/VideoMultiAgents.
Authors: Ziyang Xu, Kangsheng Duan, Xiaolei Shen, Zhifeng Ding, Wenyu Liu, Xiaohu Ruan, Xiaoxin Chen, Xinggang Wang
Abstract: Image inpainting is a fundamental research area between image editing and image generation. Recent state-of-the-art (SOTA) methods have explored novel attention mechanisms, lightweight architectures, and context-aware modeling, demonstrating impressive performance. However, they often struggle with complex structure (e.g., texture, shape, spatial relations) and semantics (e.g., color consistency, object restoration, and logical correctness), leading to artifacts and inappropriate generation. To address this challenge, we design a simple yet effective inpainting paradigm called latent categories guidance, and further propose a diffusion-based model named PixelHacker. Specifically, we first construct a large dataset containing 14 million image-mask pairs by annotating foreground and background (potential 116 and 21 categories, respectively). Then, we encode potential foreground and background representations separately through two fixed-size embeddings, and intermittently inject these features into the denoising process via linear attention. Finally, by pre-training on our dataset and fine-tuning on open-source benchmarks, we obtain PixelHacker. Extensive experiments show that PixelHacker comprehensively outperforms the SOTA on a wide range of datasets (Places2, CelebA-HQ, and FFHQ) and exhibits remarkable consistency in both structure and semantics. Project page at https://hustvl.github.io/PixelHacker.
Authors: Yanghui Song, Chengfu Yang
Abstract: Given the severe challenges confronting the global growth security of economic crops, precise identification and prevention of plant diseases has emerged as a critical issue in artificial intelligence-enabled agricultural technology. To address the technical challenges in plant disease recognition, including small-sample learning, leaf occlusion, illumination variations, and high inter-class similarity, this study innovatively proposes a Dynamic Dual-Stream Fusion Network (DS_FusionNet). The network integrates a dual-backbone architecture, deformable dynamic fusion modules, and bidirectional knowledge distillation strategy, significantly enhancing recognition accuracy. Experimental results demonstrate that DS_FusionNet achieves classification accuracies exceeding 90% using only 10% of the PlantDisease and CIFAR-10 datasets, while maintaining 85% accuracy on the complex PlantWild dataset, exhibiting exceptional generalization capabilities. This research not only provides novel technical insights for fine-grained image classification but also establishes a robust foundation for precise identification and management of agricultural diseases.
Authors: Yaoxian Song, Penglei Sun, Piaopiao Jin, Yi Ren, Yu Zheng, Zhixu Li, Xiaowen Chu, Yue Zhang, Tiefeng Li, Jason Gu
Abstract: Robotic grasping is a fundamental ability for a robot to interact with the environment. Current methods focus on how to obtain a stable and reliable grasping pose in object level, while little work has been studied on part (shape)-wise grasping which is related to fine-grained grasping and robotic affordance. Parts can be seen as atomic elements to compose an object, which contains rich semantic knowledge and a strong correlation with affordance. However, lacking a large part-wise 3D robotic dataset limits the development of part representation learning and downstream applications. In this paper, we propose a new large Language-guided SHape grAsPing datasEt (named LangSHAPE) to promote 3D part-level affordance and grasping ability learning. From the perspective of robotic cognition, we design a two-stage fine-grained robotic grasping framework (named LangPartGPD), including a novel 3D part language grounding model and a part-aware grasp pose detection model, in which explicit language input from human or large language models (LLMs) could guide a robot to generate part-level 6-DoF grasping pose with textual explanation. Our method combines the advantages of human-robot collaboration and LLMs' planning ability using explicit language as a symbolic intermediate. To evaluate the effectiveness of our proposed method, we perform 3D part grounding and fine-grained grasp detection experiments on both simulation and physical robot settings, following language instructions across different degrees of textual complexity. Results show our method achieves competitive performance in 3D geometry fine-grained grounding, object affordance inference, and 3D part-aware grasping tasks. Our dataset and code are available on our project website https://sites.google.com/view/lang-shape
Authors: Lukas Sch\"afer, Logan Jones, Anssi Kanervisto, Yuhan Cao, Tabish Rashid, Raluca Georgescu, Dave Bignell, Siddhartha Sen, Andrea Trevi\~no Gavito, Sam Devlin
Abstract: Video games have served as useful benchmarks for the decision-making community, but going beyond Atari games towards modern games has been prohibitively expensive for the vast majority of the research community. Prior work in modern video games typically relied on game-specific integration to obtain game features and enable online training, or on existing large datasets. An alternative approach is to train agents using imitation learning to play video games purely from images. However, this setting poses a fundamental question: which visual encoders obtain representations that retain information critical for decision making? To answer this question, we conduct a systematic study of imitation learning with publicly available pre-trained visual encoders compared to the typical task-specific end-to-end training approach in Minecraft, Counter-Strike: Global Offensive, and Minecraft Dungeons. Our results show that end-to-end training can be effective with comparably low-resolution images and only minutes of demonstrations, but significant improvements can be gained by utilising pre-trained encoders such as DINOv2 depending on the game. In addition to enabling effective decision making, we show that pre-trained encoders can make decision-making research in video games more accessible by significantly reducing the cost of training.
Authors: Damien Teney, Armand Nicolicioiu, Valentin Hartmann, Ehsan Abbasnejad
Abstract: Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free methods nor the simplicity bias recently observed in untrained networks. This paper seeks other sources of generalization in NNs. Findings. To understand the inductive biases provided by architectures independently from GD, we examine untrained, random-weight networks. Even simple MLPs show strong inductive biases: uniform sampling in weight space yields a very biased distribution of functions in terms of complexity. But unlike common wisdom, NNs do not have an inherent "simplicity bias". This property depends on components such as ReLUs, residual connections, and layer normalizations. Alternative architectures can be built with a bias for any level of complexity. Transformers also inherit all these properties from their building blocks. Implications. We provide a fresh explanation for the success of deep learning independent from gradient-based training. It points at promising avenues for controlling the solutions implemented by trained models.
Authors: Ruiping Liu, Jiaming Zhang, Angela Sch\"on, Karin M\"uller, Junwei Zheng, Kailun Yang, Anhong Guo, Kathrin Gerling, Rainer Stiefelhagen
Abstract: Searching for objects in unfamiliar scenarios is a challenging task for blind people. It involves specifying the target object, detecting it, and then gathering detailed information according to the user's intent. However, existing description- and detection-based assistive technologies do not sufficiently support the multifaceted nature of interactive object search tasks. We present ObjectFinder, an open-vocabulary wearable assistive system for interactive object search by blind people. ObjectFinder allows users to query target objects using flexible wording. Once the target object is detected, it provides egocentric localization information in real-time, including distance and direction. Users can then initiate different branches to gather detailed information based on their intent towards the target object, such as navigating to it or perceiving its surroundings. ObjectFinder is powered by a seamless combination of open-vocabulary models, namely an open-vocabulary object detector and a multimodal large language model. The ObjectFinder design concept and its development were carried out in collaboration with a blind co-designer. To evaluate ObjectFinder, we conducted an exploratory user study with eight blind participants. We compared ObjectFinder to BeMyAI and Google Lookout, popular description- and detection-based assistive applications. Our findings indicate that most participants felt more independent with ObjectFinder and preferred it for object search, as it enhanced scene context gathering and navigation, and allowed for active target identification. Finally, we discuss the implications for future assistive systems to support interactive object search.
Authors: Yijie Dang, Weijun Ma, Xiaohu Luo, Huaizhu Wang
Abstract: Since the outbreak of the COVID-19 pandemic in 2019, medical imaging has emerged as a primary modality for diagnosing COVID-19 pneumonia. In clinical settings, the segmentation of lung infections from computed tomography images enables rapid and accurate quantification and diagnosis of COVID-19. Segmentation of COVID-19 infections in the lungs poses a formidable challenge, primarily due to the indistinct boundaries and limited contrast presented by ground glass opacity manifestations. Moreover, the confounding similarity between infiltrates, lung tissues, and lung walls further complicates this segmentation task. To address these challenges, this paper introduces a novel deep network architecture, called CAD-Unet, for segmenting COVID-19 lung infections. In this architecture, capsule networks are incorporated into the existing Unet framework. Capsule networks represent a novel network architecture that differs from traditional convolutional neural networks. They utilize vectors for information transfer among capsules, facilitating the extraction of intricate lesion spatial information. Additionally, we design a capsule encoder path and establish a coupling path between the unet encoder and the capsule encoder. This design maximizes the complementary advantages of both network structures while achieving efficient information fusion. \noindent Finally, extensive experiments are conducted on four publicly available datasets, encompassing binary segmentation tasks and multi-class segmentation tasks. The experimental results demonstrate the superior segmentation performance of the proposed model. The code has been released at: https://github.com/AmanoTooko-jie/CAD-Unet.
Authors: Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu
Abstract: Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. Despite their utility in advancing digital automation, a critical bottleneck persists: collecting high-quality trajectory data for training. Common practices for collecting such data rely on human supervision or synthetic data generation through executing pre-defined tasks, which are either resource-intensive or unable to guarantee data quality. Moreover, these methods suffer from limited data diversity and significant gaps between synthetic data and real-world environments. To address these challenges, we propose OS-Genesis, a novel GUI data synthesis pipeline that reverses the conventional trajectory collection process. Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions, then retrospectively derive high-quality tasks to enable trajectory-level exploration. A trajectory reward model is then employed to ensure the quality of the generated trajectories. We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks. In-depth analysis further validates OS-Genesis's efficiency and its superior data quality and diversity compared to existing synthesis methods. Our codes, data, and checkpoints are available at https://qiushisun.github.io/OS-Genesis-Home/.
Authors: Daniel Sikar, Artur d'Avila Garcez, Tillman Weyde
Abstract: Ensuring the reliability of automated decision-making based on neural networks will be crucial as Artificial Intelligence systems are deployed more widely in critical situations. This paper proposes a new approach for measuring confidence in the predictions of any neural network that relies on the predictions of a softmax layer. We identify that a high-accuracy trained network may have certain outputs for which there should be low confidence. In such cases, decisions should be deferred and it is more appropriate for the network to provide a \textit{not known} answer to a corresponding classification task. Our approach clusters the vectors in the softmax layer to measure distances between cluster centroids and network outputs. We show that a cluster with centroid calculated simply as the mean softmax output for all correct predictions can serve as a suitable proxy in the evaluation of confidence. Defining a distance threshold for a class as the smallest distance from an incorrect prediction to the given class centroid offers a simple approach to adding \textit{not known} answers to any network classification falling outside of the threshold. We evaluate the approach on the MNIST and CIFAR-10 datasets using a Convolutional Neural Network and a Vision Transformer, respectively. The results show that our approach is consistent across datasets and network models, and indicate that the proposed distance metric can offer an efficient way of determining when automated predictions are acceptable and when they should be deferred to human operators.
Authors: Kaiwen Zheng, Guande He, Jianfei Chen, Fan Bao, Jun Zhu
Abstract: Consistency distillation is a prevalent way for accelerating diffusion models adopted in consistency (trajectory) models, in which a student model is trained to traverse backward on the probability flow (PF) ordinary differential equation (ODE) trajectory determined by the teacher model. Preconditioning is a vital technique for stabilizing consistency distillation, by linear combining the input data and the network output with pre-defined coefficients as the consistency function. It imposes the boundary condition of consistency functions without restricting the form and expressiveness of the neural network. However, previous preconditionings are hand-crafted and may be suboptimal choices. In this work, we offer the first theoretical insights into the preconditioning in consistency distillation, by elucidating its design criteria and the connection to the teacher ODE trajectory. Based on these analyses, we further propose a principled way dubbed \textit{Analytic-Precond} to analytically optimize the preconditioning according to the consistency gap (defined as the gap between the teacher denoiser and the optimal student denoiser) on a generalized teacher ODE. We demonstrate that Analytic-Precond can facilitate the learning of trajectory jumpers, enhance the alignment of the student trajectory with the teacher's, and achieve $2\times$ to $3\times$ training acceleration of consistency trajectory models in multi-step generation across various datasets.
Authors: Ao liu, Zelin Zhang, Songbai Chen, Cuihong Wen, Jieci Wang
Abstract: The properties of black holes and accretion flows can be inferred by fitting Event Horizon Telescope (EHT) data to simulated images generated through general relativistic ray tracing (GRRT). However, due to the computationally intensive nature of GRRT, the efficiency of generating specific radiation flux images needs to be improved. This paper introduces the Branch Correction Denoising Diffusion Model (BCDDM), which uses a branch correction mechanism and a weighted mixed loss function to improve the accuracy of generated black hole images based on seven physical parameters of the radiatively inefficient accretion flow (RIAF) model. Our experiments show a strong correlation between the generated images and their physical parameters. By enhancing the GRRT dataset with BCDDM-generated images and using ResNet50 for parameter regression, we achieve significant improvements in parameter prediction performance. This approach reduces computational costs and provides a faster, more efficient method for dataset expansion, parameter estimation, and model fitting.
Authors: Saqib Qamar, Syed Furqan Qadri, Roobaea Alroobaea, Goram Mufarah M Alshmrani, Richard Jiang
Abstract: Melanoma is a malignant tumor originating from skin cell lesions. Accurate and efficient segmentation of skin lesions is essential for quantitative medical analysis but remains challenging. To address this, we propose ScaleFusionNet, a segmentation model that integrates Cross-Attention Transformer Module (CATM) and AdaptiveFusionBlock to enhance feature extraction and fusion. The model employs a hybrid architecture encoder that effectively captures both local and global features. We introduce CATM, which utilizes Swin Transformer Blocks and Cross Attention Fusion (CAF) to adaptively refine encoder-decoder feature fusion, reducing semantic gaps and improving segmentation accuracy. Additionally, the AdaptiveFusionBlock is improved by integrating adaptive multi-scale fusion, where Swin Transformer-based attention complements deformable convolution-based multi-scale feature extraction. This enhancement refines lesion boundaries and preserves fine-grained details. ScaleFusionNet achieves Dice scores of 92.94% and 91.65% on ISIC-2016 and ISIC-2018 datasets, respectively, demonstrating its effectiveness in skin lesion analysis. Our code implementation is publicly available at GitHub.
Authors: AgiBot-World-Contributors, Qingwen Bu, Jisong Cai, Li Chen, Xiuqi Cui, Yan Ding, Siyuan Feng, Shenyuan Gao, Xindong He, Xuan Hu, Xu Huang, Shu Jiang, Yuxin Jiang, Cheng Jing, Hongyang Li, Jialu Li, Chiming Liu, Yi Liu, Yuxiang Lu, Jianlan Luo, Ping Luo, Yao Mu, Yuehan Niu, Yixuan Pan, Jiangmiao Pang, Yu Qiao, Guanghui Ren, Cheng Ruan, Jiaqi Shan, Yongjian Shen, Chengshi Shi, Mingkang Shi, Modi Shi, Chonghao Sima, Jianheng Song, Huijie Wang, Wenhao Wang, Dafeng Wei, Chengen Xie, Guo Xu, Junchi Yan, Cunbiao Yang, Lei Yang, Shukai Yang, Maoqing Yao, Jia Zeng, Chi Zhang, Qinglin Zhang, Bin Zhao, Chengyue Zhao, Jiaqi Zhao, Jianchao Zhu
Abstract: We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence.
Authors: Tianyu Chen, Xingcheng Fu, Yisen Gao, Haodong Qian, Yuecen Wei, Kun Yan, Haoyi Zhou, Jianxin Li
Abstract: Modern vision-language models (VLMs) develop patch embedding and convolution backbone within vector space, especially Euclidean ones, at the very founding. When expanding VLMs to a galaxy scale for understanding astronomical phenomena, the integration of spherical space for planetary orbits and hyperbolic spaces for black holes raises two formidable challenges. a) The current pre-training model is confined to Euclidean space rather than a comprehensive geometric embedding. b) The predominant architecture lacks suitable backbones for anisotropic physical geometries. In this paper, we introduced Galaxy-Walker, a geometry-aware VLM, for the universe-level vision understanding tasks. We proposed the geometry prompt that generates geometry tokens by random walks across diverse spaces on a multi-scale physical graph, along with a geometry adapter that compresses and reshapes the space anisotropy in a mixture-of-experts manner. Extensive experiments demonstrate the effectiveness of our approach, with Galaxy-Walker achieving state-of-the-art performance in both galaxy property estimation ($R^2$ scores up to $0.91$) and morphology classification tasks (up to $+0.17$ F1 improvement in challenging features), significantly outperforming both domain-specific models and general-purpose VLMs.
Authors: Andrea Di Pierno (IMT School of Advanced Studies, Lucca, Italy, Department of Mathematics and Computer Science, University of Catania, Italy), Luca Guarnera (Department of Mathematics and Computer Science, University of Catania, Italy), Dario Allegra (Department of Mathematics and Computer Science, University of Catania, Italy), Sebastiano Battiato (Department of Mathematics and Computer Science, University of Catania, Italy)
Abstract: Audio deepfakes represent a growing threat to digital security and trust, leveraging advanced generative models to produce synthetic speech that closely mimics real human voices. Detecting such manipulations is especially challenging under open-world conditions, where spoofing methods encountered during testing may differ from those seen during training. In this work, we propose an end-to-end deep learning framework for audio deepfake detection that operates directly on raw waveforms. Our model, RawNetLite, is a lightweight convolutional-recurrent architecture designed to capture both spectral and temporal features without handcrafted preprocessing. To enhance robustness, we introduce a training strategy that combines data from multiple domains and adopts Focal Loss to emphasize difficult or ambiguous samples. We further demonstrate that incorporating codec-based manipulations and applying waveform-level audio augmentations (e.g., pitch shifting, noise, and time stretching) leads to significant generalization improvements under realistic acoustic conditions. The proposed model achieves over 99.7% F1 and 0.25% EER on in-domain data (FakeOrReal), and up to 83.4% F1 with 16.4% EER on a challenging out-of-distribution test set (AVSpoof2021 + CodecFake). These findings highlight the importance of diverse training data, tailored objective functions and audio augmentations in building resilient and generalizable audio forgery detectors. Code and pretrained models are available at https://iplab.dmi.unict.it/mfs/Deepfakes/PaperRawNet2025/.
URLs: https://iplab.dmi.unict.it/mfs/Deepfakes/PaperRawNet2025/.