Authors: Ruben Gonzalez Avil\'es, Linus Scheibenreif, Damian Borth
Abstract: This paper addresses the critical environmental challenge of estimating ambient Nitrogen Dioxide (NO$_2$) concentrations, a key issue in public health and environmental policy. Existing methods for satellite-based air pollution estimation model the relationship between satellite and in-situ measurements at select point locations. While these approaches have advanced our ability to provide air quality estimations on a global scale, they come with inherent limitations. The most notable limitation is the computational intensity required for generating comprehensive estimates over extensive areas. Motivated by these limitations, this study introduces a novel dense estimation technique. Our approach seeks to balance the accuracy of high-resolution estimates with the practicality of computational constraints, thereby enabling efficient and scalable global environmental assessment. By utilizing a uniformly random offset sampling strategy, our method disperses the ground truth data pixel location evenly across a larger patch. At inference, the dense estimation method can then generate a grid of estimates in a single step, significantly reducing the computational resources required to provide estimates for larger areas. Notably, our approach also surpasses the results of existing point-wise methods by a significant margin of $9.45\%$, achieving a Mean Absolute Error (MAE) of $4.98\ \mu\text{g}/\text{m}^3$. This demonstrates both high accuracy and computational efficiency, highlighting the applicability of our method for global environmental assessment. Furthermore, we showcase the method's adaptability and robustness by applying it to diverse geographic regions. Our method offers a viable solution to the computational challenges of large-scale environmental monitoring.
Authors: Zhenhailong Wang, Senthil Purushwalkam, Caiming Xiong, Silvio Savarese, Heng Ji, Ran Xu
Abstract: We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity, addressing the inherent inefficiency of fixed-length outputs in vision transformers. Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence, thus preserving the downstream performance without additional fine-tuning. Unlike previous approaches, our method dynamically adapts token compression to the content of the image and operates completely training-free, making it readily applicable to most state-of-the-art VLM architectures. Extensive experiments on image and video understanding tasks demonstrate that DyMU can reduce the average visual token count by 32%-85% while achieving comparable performance to full-length models across diverse VLM architectures, including the recently popularized AnyRes-based visual encoders. Furthermore, through qualitative analyses, we demonstrate that DToMe effectively adapts token reduction based on image complexity and, unlike existing systems, provides users more control over computational costs. Project page: https://mikewangwzhl.github.io/dymu/.
Authors: Xinqi Xiong, Andrea Dunn Beltran, Jun Myeong Choi, Marc Niethammer, Roni Sengupta
Abstract: Accurate depth estimation enhances endoscopy navigation and diagnostics, but obtaining ground-truth depth in clinical settings is challenging. Synthetic datasets are often used for training, yet the domain gap limits generalization to real data. We propose a novel image-to-image translation framework that preserves structure while generating realistic textures from clinical data. Our key innovation integrates Stable Diffusion with ControlNet, conditioned on a latent representation extracted from a Per-Pixel Shading (PPS) map. PPS captures surface lighting effects, providing a stronger structural constraint than depth maps. Experiments show our approach produces more realistic translations and improves depth estimation over GAN-based MI-CycleGAN. Our code is publicly accessible at https://github.com/anaxqx/PPS-Ctrl.
Authors: Rishav Pramanik, Antoine Poupon, Juan A. Rodriguez, Masih Aminbeidokhti, David Vazquez, Christopher Pal, Zhaozheng Yin, Marco Pedersoli
Abstract: Autoregressive patch-based image generation has recently shown competitive results in terms of image quality and scalability. It can also be easily integrated and scaled within Vision-Language models. Nevertheless, autoregressive models require a defined order for patch generation. While a natural order based on the dictation of the words makes sense for text generation, there is no inherent generation order that exists for image generation. Traditionally, a raster-scan order (from top-left to bottom-right) guides autoregressive image generation models. In this paper, we argue that this order is suboptimal, as it fails to respect the causality of the image content: for instance, when conditioned on a visual description of a sunset, an autoregressive model may generate clouds before the sun, even though the color of clouds should depend on the color of the sun and not the inverse. In this work, we show that first by training a model to generate patches in any-given-order, we can infer both the content and the location (order) of each patch during generation. Secondly, we use these extracted orders to finetune the any-given-order model to produce better-quality images. Through our experiments, we show on two datasets that this new generation method produces better images than the traditional raster-scan approach, with similar training costs and no extra annotations.
Authors: Jens Petersen, Davide Abati, Amirhossein Habibian, Auke Wiggers
Abstract: Generative image models are increasingly being used for training data augmentation in vision tasks. In the context of automotive object detection, methods usually focus on producing augmented frames that look as realistic as possible, for example by replacing real objects with generated ones. Others try to maximize the diversity of augmented frames, for example by pasting lots of generated objects onto existing backgrounds. Both perspectives pay little attention to the locations of objects in the scene. Frame layouts are either reused with little or no modification, or they are random and disregard realism entirely. In this work, we argue that optimal data augmentation should also include realistic augmentation of layouts. We introduce a scene-aware probabilistic location model that predicts where new objects can realistically be placed in an existing scene. By then inpainting objects in these locations with a generative model, we obtain much stronger augmentation performance than existing approaches. We set a new state of the art for generative data augmentation on two automotive object detection tasks, achieving up to $2.8\times$ higher gains than the best competing approach ($+1.4$ vs. $+0.5$ mAP boost). We also demonstrate significant improvements for instance segmentation.
Authors: Tekin Gunasar, Virginia de Sa
Abstract: We propose a method to improve subject transfer in motor imagery BCIs by aligning covariance matrices on a Riemannian manifold, followed by computing a new common spatial patterns (CSP) based spatial filter. We explore various ways to integrate information from multiple subjects and show improved performance compared to standard CSP. Across three datasets, our method shows marginal improvements over standard CSP; however, when training data are limited, the improvements become more significant.
Authors: Ning Li, Antai Andy Liu, Jingran Zhang, Justin Cui
Abstract: Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existing video dataset distillation methods primarily focus on compression in the pixel space, overlooking advances in the latent space that have been widely adopted in modern text-to-image and text-to-video models. In this work, we bridge this gap by introducing a novel video dataset distillation approach that operates in the latent space using a state-of-the-art variational encoder. Furthermore, we employ a diversity-aware data selection strategy to select both representative and diverse samples. Additionally, we introduce a simple, training-free method to further compress the distilled latent dataset. By combining these techniques, our approach achieves a new state-of-the-art performance in dataset distillation, outperforming prior methods on all datasets, e.g. on HMDB51 IPC 1, we achieve a 2.6% performance increase; on MiniUCF IPC 5, we achieve a 7.8% performance increase.
Authors: Cece Zhang, Xuehuan Zhu, Nick Peterson, Jieqiong Wang, Shibiao Wan
Abstract: The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, plays a critical role in determining their biological functions. For instance, lncRNAs are predominantly associated with chromatin and act as regulators of gene transcription and chromatin structure, while mRNAs are distributed across the nucleus and cytoplasm, facilitating the transport of genetic information for protein synthesis. Understanding RNA localization sheds light on processes like gene expression regulation with spatial and temporal precision. However, traditional wet lab methods for determining RNA localization, such as in situ hybridization, are often time-consuming, resource-demanding, and costly. To overcome these challenges, computational methods leveraging artificial intelligence (AI) and machine learning (ML) have emerged as powerful alternatives, enabling large-scale prediction of RNA subcellular localization. This paper provides a comprehensive review of the latest advancements in AI-based approaches for RNA subcellular localization prediction, covering various RNA types and focusing on sequence-based, image-based, and hybrid methodologies that combine both data types. We highlight the potential of these methods to accelerate RNA research, uncover molecular pathways, and guide targeted disease treatments. Furthermore, we critically discuss the challenges in AI/ML approaches for RNA subcellular localization, such as data scarcity and lack of benchmarks, and opportunities to address them. This review aims to serve as a valuable resource for researchers seeking to develop innovative solutions in the field of RNA subcellular localization and beyond.
Authors: Kai Cui, Jia Li, Yu Liu, Xuesong Zhang, Zhenzhen Hu, Meng Wang
Abstract: Electroencephalography (EEG) signals provide a promising and involuntary reflection of brain activity related to emotional states, offering significant advantages over behavioral cues like facial expressions. However, EEG signals are often noisy, affected by artifacts, and vary across individuals, complicating emotion recognition. While multimodal approaches have used Peripheral Physiological Signals (PPS) like GSR to complement EEG, they often overlook the dynamic synchronization and consistent semantics between the modalities. Additionally, the temporal dynamics of emotional fluctuations across different time resolutions in PPS remain underexplored. To address these challenges, we propose PhysioSync, a novel pre-training framework leveraging temporal and cross-modal contrastive learning, inspired by physiological synchronization phenomena. PhysioSync incorporates Cross-Modal Consistency Alignment (CM-CA) to model dynamic relationships between EEG and complementary PPS, enabling emotion-related synchronizations across modalities. Besides, it introduces Long- and Short-Term Temporal Contrastive Learning (LS-TCL) to capture emotional synchronization at different temporal resolutions within modalities. After pre-training, cross-resolution and cross-modal features are hierarchically fused and fine-tuned to enhance emotion recognition. Experiments on DEAP and DREAMER datasets demonstrate PhysioSync's advanced performance under uni-modal and cross-modal conditions, highlighting its effectiveness for EEG-centered emotion recognition.
Authors: Kevin Lane, Morteza Karimzadeh
Abstract: Foundation models have garnered increasing attention for representation learning in remote sensing, primarily adopting approaches that have demonstrated success in computer vision with minimal domain-specific modification. However, the development and application of foundation models in this field are still burgeoning, as there are a variety of competing approaches that each come with significant benefits and drawbacks. This paper examines these approaches along with their roots in the computer vision field in order to characterize potential advantages and pitfalls while outlining future directions to further improve remote sensing-specific foundation models. We discuss the quality of the learned representations and methods to alleviate the need for massive compute resources. We place emphasis on the multi-sensor aspect of Earth observations, and the extent to which existing approaches leverage multiple sensors in training foundation models in relation to multi-modal foundation models. Finally, we identify opportunities for further harnessing the vast amounts of unlabeled, seasonal, and multi-sensor remote sensing observations.
Authors: Minkyu Choi, S P Sharan, Harsh Goel, Sahil Shah, Sandeep Chinchali
Abstract: Current text-to-video (T2V) generation models are increasingly popular due to their ability to produce coherent videos from textual prompts. However, these models often struggle to generate semantically and temporally consistent videos when dealing with longer, more complex prompts involving multiple objects or sequential events. Additionally, the high computational costs associated with training or fine-tuning make direct improvements impractical. To overcome these limitations, we introduce \(\projectname\), a novel zero-training video refinement pipeline that leverages neuro-symbolic feedback to automatically enhance video generation, achieving superior alignment with the prompts. Our approach first derives the neuro-symbolic feedback by analyzing a formal video representation and pinpoints semantically inconsistent events, objects, and their corresponding frames. This feedback then guides targeted edits to the original video. Extensive empirical evaluations on both open-source and proprietary T2V models demonstrate that \(\projectname\) significantly enhances temporal and logical alignment across diverse prompts by almost $40\%$.
Authors: Phillip Y. Lee, Jihyeon Je, Chanho Park, Mikaela Angelina Uy, Leonidas Guibas, Minhyuk Sung
Abstract: We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Perspective-taking, the ability to perceive an environment or situation from an alternative viewpoint, is a key benchmark for human-level visual understanding, essential for environmental interaction and collaboration with autonomous agents. Despite advancements in spatial reasoning within VLMs, recent research has shown that modern VLMs significantly lack perspective-aware reasoning capabilities and exhibit a strong bias toward egocentric interpretations. To bridge the gap between VLMs and human perception, we focus on the role of mental imagery, where humans perceive the world through abstracted representations that facilitate perspective shifts. Motivated by this, we propose a framework for perspective-aware reasoning, named Abstract Perspective Change (APC), that effectively leverages vision foundation models, such as object detection, segmentation, and orientation estimation, to construct scene abstractions and enable perspective transformations. Our experiments on synthetic and real-image benchmarks, compared with various VLMs, demonstrate significant improvements in perspective-aware reasoning with our framework, further outperforming fine-tuned spatial reasoning models and novel-view-synthesis-based approaches.
Authors: Shiwen Cao, Zhaoxing Zhang, Junming Jiao, Juyi Qiao, Guowen Song, Rong Shen
Abstract: Even in the era of rapid advances in large models, video understanding, particularly long videos, remains highly challenging. Compared with textual or image-based information, videos commonly contain more information with redundancy, requiring large models to strategically allocate attention at a global level for accurate comprehension. To address this, we propose MCAF, an agent-based, training-free framework perform video understanding through Multimodal Coarse-to-fine Attention Focusing. The key innovation lies in its ability to sense and prioritize segments of the video that are highly relevant to the understanding task. First, MCAF hierarchically concentrates on highly relevant frames through multimodal information, enhancing the correlation between the acquired contextual information and the query. Second, it employs a dilated temporal expansion mechanism to mitigate the risk of missing crucial details when extracting information from these concentrated frames. In addition, our framework incorporates a self-reflection mechanism utilizing the confidence level of the model's responses as feedback. By iteratively applying these two creative focusing strategies, it adaptively adjusts attention to capture highly query-connected context and thus improves response accuracy. MCAF outperforms comparable state-of-the-art methods on average. On the EgoSchema dataset, it achieves a remarkable 5% performance gain over the leading approach. Meanwhile, on Next-QA and IntentQA datasets, it outperforms the current state-of-the-art standard by 0.2% and 0.3% respectively. On the Video-MME dataset, which features videos averaging nearly an hour in length, MCAF also outperforms other agent-based methods.
Authors: Mengyu Qiao, Runze Tian, Yang Wang
Abstract: The rapid evolution of deep generative models poses a critical challenge to deepfake detection, as detectors trained on forgery-specific artifacts often suffer significant performance degradation when encountering unseen forgeries. While existing methods predominantly rely on spatial domain analysis, frequency domain operations are primarily limited to feature-level augmentation, leaving frequency-native artifacts and spatial-frequency interactions insufficiently exploited. To address this limitation, we propose a novel detection framework that integrates multi-scale spatial-frequency analysis for universal deepfake detection. Our framework comprises three key components: (1) a local spectral feature extraction pipeline that combines block-wise discrete cosine transform with cascaded multi-scale convolutions to capture subtle spectral artifacts; (2) a global spectral feature extraction pipeline utilizing scale-invariant differential accumulation to identify holistic forgery distribution patterns; and (3) a multi-stage cross-modal fusion mechanism that incorporates shallow-layer attention enhancement and deep-layer dynamic modulation to model spatial-frequency interactions. Extensive evaluations on widely adopted benchmarks demonstrate that our method outperforms state-of-the-art deepfake detection methods in both accuracy and generalizability.
Authors: Zhifeng Wang, Qixuan Zhang, Peter Zhang, Wenjia Niu, Kaihao Zhang, Ramesh Sankaranarayana, Sabrina Caldwell, Tom Gedeon
Abstract: Vision Large Language Models (VLLMs) exhibit promising potential for multi-modal understanding, yet their application to video-based emotion recognition remains limited by insufficient spatial and contextual awareness. Traditional approaches, which prioritize isolated facial features, often neglect critical non-verbal cues such as body language, environmental context, and social interactions, leading to reduced robustness in real-world scenarios. To address this gap, we propose Set-of-Vision-Text Prompting (SoVTP), a novel framework that enhances zero-shot emotion recognition by integrating spatial annotations (e.g., bounding boxes, facial landmarks), physiological signals (facial action units), and contextual cues (body posture, scene dynamics, others' emotions) into a unified prompting strategy. SoVTP preserves holistic scene information while enabling fine-grained analysis of facial muscle movements and interpersonal dynamics. Extensive experiments show that SoVTP achieves substantial improvements over existing visual prompting methods, demonstrating its effectiveness in enhancing VLLMs' video emotion recognition capabilities.
Authors: Akihiro Kuwabara, Sorachi Kato, Takuya Fujihashi, Toshiaki Koike-Akino, Takashi Watanabe
Abstract: This paper presents a novel scheme to efficiently compress Light Detection and Ranging~(LiDAR) point clouds, enabling high-precision 3D scene archives, and such archives pave the way for a detailed understanding of the corresponding 3D scenes. We focus on 2D range images~(RIs) as a lightweight format for representing 3D LiDAR observations. Although conventional image compression techniques can be adapted to improve compression efficiency for RIs, their practical performance is expected to be limited due to differences in bit precision and the distinct pixel value distribution characteristics between natural images and RIs. We propose a novel implicit neural representation~(INR)--based RI compression method that effectively handles floating-point valued pixels. The proposed method divides RIs into depth and mask images and compresses them using patch-wise and pixel-wise INR architectures with model pruning and quantization, respectively. Experiments on the KITTI dataset show that the proposed method outperforms existing image, point cloud, RI, and INR-based compression methods in terms of 3D reconstruction and detection quality at low bitrates and decoding latency.
Authors: Zhiqiang Lao, Heather Yu
Abstract: The rapid advancement of artificial intelligence and widespread use of smartphones have resulted in an exponential growth of image data, both real (camera-captured) and virtual (AI-generated). This surge underscores the critical need for robust image quality assessment (IQA) methods that accurately reflect human visual perception. Traditional IQA techniques primarily rely on spatial features - such as signal-to-noise ratio, local structural distortions, and texture inconsistencies - to identify artifacts. While effective for unprocessed or conventionally altered images, these methods fall short in the context of modern image post-processing powered by deep neural networks (DNNs). The rise of DNN-based models for image generation, enhancement, and restoration has significantly improved visual quality, yet made accurate assessment increasingly complex. To address this, we propose a novel IQA approach that bridges the gap between deep learning methods and human perception. Our model disentangles deep features into high-level semantic information and low-level perceptual details, treating each stream separately. These features are then combined with conventional IQA metrics to provide a more comprehensive evaluation framework. This hybrid design enables the model to assess both global context and intricate image details, better reflecting the human visual process, which first interprets overall structure before attending to fine-grained elements. The final stage employs a multilayer perceptron (MLP) to map the integrated features into a concise quality score. Experimental results demonstrate that our method achieves improved consistency with human perceptual judgments compared to existing IQA models.
Authors: Yinqi Li, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen
Abstract: Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we extend the discriminative capability of pretrained frozen generative diffusion models from the classification task to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model. To this end, a gradient-based discrete optimization approach for replacing the heavy prediction enumeration process, and a prior distribution model for making more accurate use of the Bayes' rule, are proposed respectively. Empirical results show that this method is on par with basic discriminative object detection baselines on COCO dataset. In addition, our method can greatly speed up the previous diffusion-based method for classification without sacrificing accuracy. Code and models are available at https://github.com/LiYinqi/DIVE .
Authors: Wenqiang Zhou, Zhendong Yu, Xinyu Liu, Jiaming Yang, Rong Xiao, Tao Wang, Chenwei Tang, Jiancheng Lv
Abstract: Quantization Aware Training (QAT) is a neural network quantization technique that compresses model size and improves operational efficiency while effectively maintaining model performance. The paradigm of QAT is to introduce fake quantization operators during the training process, allowing the model to autonomously compensate for information loss caused by quantization. Making quantization parameters trainable can significantly improve the performance of QAT, but at the cost of compromising the flexibility during inference, especially when dealing with activation values with substantially different distributions. In this paper, we propose an effective learnable adaptive neural network quantization method, called Adaptive Step Size Quantization (ASQ), to resolve this conflict. Specifically, the proposed ASQ method first dynamically adjusts quantization scaling factors through a trained module capable of accommodating different activations. Then, to address the rigid resolution issue inherent in Power of Two (POT) quantization, we propose an efficient non-uniform quantization scheme. We utilize the Power Of Square root of Two (POST) as the basis for exponential quantization, effectively handling the bell-shaped distribution of neural network weights across various bit-widths while maintaining computational efficiency through a Look-Up Table method (LUT). Extensive experimental results demonstrate that the proposed ASQ method is superior to the state-of-the-art QAT approaches. Notably that the ASQ is even competitive compared to full precision baselines, with its 4-bit quantized ResNet34 model improving accuracy by 1.2\% on ImageNet.
Authors: Yu Hong, Xiao Cai, Pengpeng Zeng, Shuai Zhang, Jingkuan Song, Lianli Gao, Heng Tao Shen
Abstract: Text-guided semantic manipulation refers to semantically editing an image generated from a source prompt to match a target prompt, enabling the desired semantic changes (e.g., addition, removal, and style transfer) while preserving irrelevant contents. With the powerful generative capabilities of the diffusion model, the task has shown the potential to generate high-fidelity visual content. Nevertheless, existing methods either typically require time-consuming fine-tuning (inefficient), fail to accomplish multiple semantic manipulations (poorly extensible), and/or lack support for different modality tasks (limited generalizability). Upon further investigation, we find that the geometric properties of noises in the diffusion model are strongly correlated with the semantic changes. Motivated by this, we propose a novel $\textit{GTF}$ for text-guided semantic manipulation, which has the following attractive capabilities: 1) $\textbf{Generalized}$: our $\textit{GTF}$ supports multiple semantic manipulations (e.g., addition, removal, and style transfer) and can be seamlessly integrated into all diffusion-based methods (i.e., Plug-and-play) across different modalities (i.e., modality-agnostic); and 2) $\textbf{Training-free}$: $\textit{GTF}$ produces high-fidelity results via simply controlling the geometric relationship between noises without tuning or optimization. Our extensive experiments demonstrate the efficacy of our approach, highlighting its potential to advance the state-of-the-art in semantics manipulation.
Authors: Haodi Yao, Fenghua He, Ning Hao, Chen Xie
Abstract: The field of keypoint extraction, which is essential for vision applications like Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM), has evolved from relying on handcrafted methods to leveraging deep learning techniques. While deep learning approaches have significantly improved performance, they often incur substantial computational costs, limiting their deployment in real-time edge applications. Efforts to create lightweight neural networks have seen some success, yet they often result in trade-offs between efficiency and accuracy. Additionally, the high-dimensional descriptors generated by these networks poses challenges for distributed applications requiring efficient communication and coordination, highlighting the need for compact yet competitively accurate descriptors. In this paper, we present EdgePoint2, a series of lightweight keypoint detection and description neural networks specifically tailored for edge computing applications on embedded system. The network architecture is optimized for efficiency without sacrificing accuracy. To train compact descriptors, we introduce a combination of Orthogonal Procrustes loss and similarity loss, which can serve as a general approach for hypersphere embedding distillation tasks. Additionally, we offer 14 sub-models to satisfy diverse application requirements. Our experiments demonstrate that EdgePoint2 consistently achieves state-of-the-art (SOTA) accuracy and efficiency across various challenging scenarios while employing lower-dimensional descriptors (32/48/64). Beyond its accuracy, EdgePoint2 offers significant advantages in flexibility, robustness, and versatility. Consequently, EdgePoint2 emerges as a highly competitive option for visual tasks, especially in contexts demanding adaptability to diverse computational and communication constraints.
Authors: Meher Boulaabi, Takwa Ben A\"icha Gader, Afef Kacem Echi, Sameh Mbarek
Abstract: To improve the segmentation of diabetic retinopathy lesions (microaneurysms, hemorrhages, exudates, and soft exudates), we implemented a binary segmentation method specific to each type of lesion. As post-segmentation, we combined the individual model outputs into a single image to better analyze the lesion types. This approach facilitated parameter optimization and improved accuracy, effectively overcoming challenges related to dataset limitations and annotation complexity. Specific preprocessing steps included cropping and applying contrast-limited adaptive histogram equalization to the L channel of the LAB image. Additionally, we employed targeted data augmentation techniques to further refine the model's efficacy. Our methodology utilized the DeepLabv3+ model, achieving a segmentation accuracy of 99%. These findings highlight the efficacy of innovative strategies in advancing medical image analysis, particularly in the precise segmentation of diabetic retinopathy lesions. The IDRID dataset was utilized to validate and demonstrate the robustness of our approach.
Authors: Zhanglin Wu, Tengfei Song, Ning Xie, Weidong Zhang, Pengfei Li, Shuang Wu, Chong Li, Junhao Zhu, Hao Yang
Abstract: This paper presents the technical solution proposed by Huawei Translation Service Center (HW-TSC) for the "End-to-End Document Image Machine Translation for Complex Layouts" competition at the 19th International Conference on Document Analysis and Recognition (DIMT25@ICDAR2025). Leveraging state-of-the-art open-source large vision-language model (LVLM), we introduce a training framework that combines multi-task learning with perceptual chain-of-thought to develop a comprehensive end-to-end document translation system. During the inference phase, we apply minimum Bayesian decoding and post-processing strategies to further enhance the system's translation capabilities. Our solution uniquely addresses both OCR-based and OCR-free document image translation tasks within a unified framework. This paper systematically details the training methods, inference strategies, LVLM base models, training data, experimental setups, and results, demonstrating an effective approach to document image machine translation.
Authors: Linli Yao, Yicheng Li, Yuancheng Wei, Lei Li, Shuhuai Ren, Yuanxin Liu, Kun Ouyang, Lean Wang, Shicheng Li, Sida Li, Lingpeng Kong, Qi Liu, Yuanxing Zhang, Xu Sun
Abstract: The rapid growth of online video platforms, particularly live streaming services, has created an urgent need for real-time video understanding systems. These systems must process continuous video streams and respond to user queries instantaneously, presenting unique challenges for current Video Large Language Models (VideoLLMs). While existing VideoLLMs excel at processing complete videos, they face significant limitations in streaming scenarios due to their inability to handle dense, redundant frames efficiently. We introduce TimeChat-Online, a novel online VideoLLM that revolutionizes real-time video interaction. At its core lies our innovative Differential Token Drop (DTD) module, which addresses the fundamental challenge of visual redundancy in streaming videos. Drawing inspiration from human visual perception's Change Blindness phenomenon, DTD preserves meaningful temporal changes while filtering out static, redundant content between frames. Remarkably, our experiments demonstrate that DTD achieves an 82.8% reduction in video tokens while maintaining 98% performance on StreamingBench, revealing that over 80% of visual content in streaming videos is naturally redundant without requiring language guidance. To enable seamless real-time interaction, we present TimeChat-Online-139K, a comprehensive streaming video dataset featuring diverse interaction patterns including backward-tracing, current-perception, and future-responding scenarios. TimeChat-Online's unique Proactive Response capability, naturally achieved through continuous monitoring of video scene transitions via DTD, sets it apart from conventional approaches. Our extensive evaluation demonstrates TimeChat-Online's superior performance on streaming benchmarks (StreamingBench and OvOBench) and maintaining competitive results on long-form video tasks such as Video-MME and MLVU.
Authors: Yiyan Xu, Wuqiang Zheng, Wenjie Wang, Fengbin Zhu, Xinting Hu, Yang Zhang, Fuli Feng, Tat-Seng Chua
Abstract: Personalized image generation has emerged as a promising direction in multimodal content creation. It aims to synthesize images tailored to individual style preferences (e.g., color schemes, character appearances, layout) and semantic intentions (e.g., emotion, action, scene contexts) by leveraging user-interacted history images and multimodal instructions. Despite notable progress, existing methods -- whether based on diffusion models, large language models, or Large Multimodal Models (LMMs) -- struggle to accurately capture and fuse user style preferences and semantic intentions. In particular, the state-of-the-art LMM-based method suffers from the entanglement of visual features, leading to Guidance Collapse, where the generated images fail to preserve user-preferred styles or reflect the specified semantics. To address these limitations, we introduce DRC, a novel personalized image generation framework that enhances LMMs through Disentangled Representation Composition. DRC explicitly extracts user style preferences and semantic intentions from history images and the reference image, respectively, to form user-specific latent instructions that guide image generation within LMMs. Specifically, it involves two critical learning stages: 1) Disentanglement learning, which employs a dual-tower disentangler to explicitly separate style and semantic features, optimized via a reconstruction-driven paradigm with difficulty-aware importance sampling; and 2) Personalized modeling, which applies semantic-preserving augmentations to effectively adapt the disentangled representations for robust personalized generation. Extensive experiments on two benchmarks demonstrate that DRC shows competitive performance while effectively mitigating the guidance collapse issue, underscoring the importance of disentangled representation learning for controllable and effective personalized image generation.
Authors: Ali Haider, Muhammad Salman Ali, Maryam Qamar, Tahir Khalil, Soo Ye Kim, Jihyong Oh, Enzo Tartaglione, Sung-Ho Bae
Abstract: Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, their inherent formulation as a regression problem makes them prone to regression to the mean, limiting their ability to capture fine details, retain high-frequency information, and handle noise effectively. To address these challenges, we propose Iterative Implicit Neural Representations (I-INRs) a novel plug-and-play framework that enhances signal reconstruction through an iterative refinement process. I-INRs effectively recover high-frequency details, improve robustness to noise, and achieve superior reconstruction quality. Our framework seamlessly integrates with existing INR architectures, delivering substantial performance gains across various tasks. Extensive experiments show that I-INRs outperform baseline methods, including WIRE, SIREN, and Gauss, in diverse computer vision applications such as image restoration, image denoising, and object occupancy prediction.
Authors: Ling You, Wenxuan Huang, Xinni Xie, Xiangyi Wei, Bangyan Li, Shaohui Lin, Yang Li, Changbo Wang
Abstract: Soccer is a globally popular sporting event, typically characterized by long matches and distinctive highlight moments. Recent advances in Multimodal Large Language Models (MLLMs) offer promising capabilities in temporal grounding and video understanding, soccer commentary generation often requires precise temporal localization and semantically rich descriptions over long-form video. However, existing soccer MLLMs often rely on the temporal a priori for caption generation, so they cannot process the soccer video end-to-end. While some traditional approaches follow a two-step paradigm that is complex and fails to capture the global context to achieve suboptimal performance. To solve the above issues, we present TimeSoccer, the first end-to-end soccer MLLM for Single-anchor Dense Video Captioning (SDVC) in full-match soccer videos. TimeSoccer jointly predicts timestamps and generates captions in a single pass, enabling global context modeling across 45-minute matches. To support long video understanding of soccer matches, we introduce MoFA-Select, a training-free, motion-aware frame compression module that adaptively selects representative frames via a coarse-to-fine strategy, and incorporates complementary training paradigms to strengthen the model's ability to handle long temporal sequences. Extensive experiments demonstrate that our TimeSoccer achieves State-of-The-Art (SoTA) performance on the SDVC task in an end-to-end form, generating high-quality commentary with accurate temporal alignment and strong semantic relevance.
Authors: Oussema Dhaouadi, Johannes Meier, Luca Wahl, Jacques Kaiser, Luca Scalerandi, Nick Wandelburg, Zhuolun Zhou, Nijanthan Berinpanathan, Holger Banzhaf, Daniel Cremers
Abstract: Accurate 3D trajectory data is crucial for advancing autonomous driving. Yet, traditional datasets are usually captured by fixed sensors mounted on a car and are susceptible to occlusion. Additionally, such an approach can precisely reconstruct the dynamic environment in the close vicinity of the measurement vehicle only, while neglecting objects that are further away. In this paper, we introduce the DeepScenario Open 3D Dataset (DSC3D), a high-quality, occlusion-free dataset of 6 degrees of freedom bounding box trajectories acquired through a novel monocular camera drone tracking pipeline. Our dataset includes more than 175,000 trajectories of 14 types of traffic participants and significantly exceeds existing datasets in terms of diversity and scale, containing many unprecedented scenarios such as complex vehicle-pedestrian interaction on highly populated urban streets and comprehensive parking maneuvers from entry to exit. DSC3D dataset was captured in five various locations in Europe and the United States and include: a parking lot, a crowded inner-city, a steep urban intersection, a federal highway, and a suburban intersection. Our 3D trajectory dataset aims to enhance autonomous driving systems by providing detailed environmental 3D representations, which could lead to improved obstacle interactions and safety. We demonstrate its utility across multiple applications including motion prediction, motion planning, scenario mining, and generative reactive traffic agents. Our interactive online visualization platform and the complete dataset are publicly available at app.deepscenario.com, facilitating research in motion prediction, behavior modeling, and safety validation.
Authors: Yiming Zhao, Guorong Li, Laiyun Qing, Amin Beheshti, Jian Yang, Michael Sheng, Yuankai Qi, Qingming Huang
Abstract: Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning strategies concentrate exclusively on text-image consistency for categories contained in training, which leads to limited generalizability for unseen categories. In this work, we propose a plug-and-play Semantic-Driven Visual Prompt Tuning framework (SDVPT) that transfers knowledge from the training set to unseen categories with minimal overhead in parameters and inference time. First, we introduce a two-stage visual prompt learning strategy composed of Category-Specific Prompt Initialization (CSPI) and Topology-Guided Prompt Refinement (TGPR). The CSPI generates category-specific visual prompts, and then TGPR distills latent structural patterns from the VLM's text encoder to refine these prompts. During inference, we dynamically synthesize the visual prompts for unseen categories based on the semantic correlation between unseen and training categories, facilitating robust text-image alignment for unseen categories. Extensive experiments integrating SDVPT with all available open-world object counting models demonstrate its effectiveness and adaptability across three widely used datasets: FSC-147, CARPK, and PUCPR+.
Authors: Francesc Marti-Escofet, Benedikt Blumenstiel, Linus Scheibenreif, Paolo Fraccaro, Konrad Schindler
Abstract: Earth observation (EO) is crucial for monitoring environmental changes, responding to disasters, and managing natural resources. In this context, foundation models facilitate remote sensing image analysis to retrieve relevant geoinformation accurately and efficiently. However, as these models grow in size, fine-tuning becomes increasingly challenging due to the associated computational resources and costs, limiting their accessibility and scalability. Furthermore, full fine-tuning can lead to forgetting pre-trained features and even degrade model generalization. To address this, Parameter-Efficient Fine-Tuning (PEFT) techniques offer a promising solution. In this paper, we conduct extensive experiments with various foundation model architectures and PEFT techniques to evaluate their effectiveness on five different EO datasets. Our results provide a comprehensive comparison, offering insights into when and how PEFT methods support the adaptation of pre-trained geospatial models. We demonstrate that PEFT techniques match or even exceed full fine-tuning performance and enhance model generalisation to unseen geographic regions, while reducing training time and memory requirements. Additional experiments investigate the effect of architecture choices such as the decoder type or the use of metadata, suggesting UNet decoders and fine-tuning without metadata as the recommended configuration. We have integrated all evaluated foundation models and techniques into the open-source package TerraTorch to support quick, scalable, and cost-effective model adaptation.
Authors: Sven Teufel, J\"org Gamerdinger, Oliver Bringmann
Abstract: Collective Perception (CP) has emerged as a promising approach to overcome the limitations of individual perception in the context of autonomous driving. Various approaches have been proposed to realize collective perception; however, the Sensor2Sensor domain gap that arises from the utilization of different sensor systems in Connected and Automated Vehicles (CAVs) remains mostly unaddressed. This is primarily due to the paucity of datasets containing heterogeneous sensor setups among the CAVs. The recently released SCOPE datasets address this issue by providing data from three different LiDAR sensors for each CAV. This study is the first to tackle the Sensor2Sensor domain gap in vehicle to vehicle (V2V) collective perception. First, we present our sensor-domain robust architecture S2S-Net. Then an in-depth analysis of the Sensor2Sensor domain adaptation capabilities of S2S-Net on the SCOPE dataset is conducted. S2S-Net demonstrates the capability to maintain very high performance in unseen sensor domains and achieved state-of-the-art results on the SCOPE dataset.
Authors: Xu Wang, Jialang Xu, Shuai Zhang, Baoru Huang, Danail Stoyanov, Evangelos B. Mazomenos
Abstract: Stereo disparity estimation is crucial for obtaining depth information in robot-assisted minimally invasive surgery (RAMIS). While current deep learning methods have made significant advancements, challenges remain in achieving an optimal balance between accuracy, robustness, and inference speed. To address these challenges, we propose the StereoMamba architecture, which is specifically designed for stereo disparity estimation in RAMIS. Our approach is based on a novel Feature Extraction Mamba (FE-Mamba) module, which enhances long-range spatial dependencies both within and across stereo images. To effectively integrate multi-scale features from FE-Mamba, we then introduce a novel Multidimensional Feature Fusion (MFF) module. Experiments against the state-of-the-art on the ex-vivo SCARED benchmark demonstrate that StereoMamba achieves superior performance on EPE of 2.64 px and depth MAE of 2.55 mm, the second-best performance on Bad2 of 41.49% and Bad3 of 26.99%, while maintaining an inference speed of 21.28 FPS for a pair of high-resolution images (1280*1024), striking the optimum balance between accuracy, robustness, and efficiency. Furthermore, by comparing synthesized right images, generated from warping left images using the generated disparity maps, with the actual right image, StereoMamba achieves the best average SSIM (0.8970) and PSNR (16.0761), exhibiting strong zero-shot generalization on the in-vivo RIS2017 and StereoMIS datasets.
Authors: Min Wei, Chaohui Yu, Jingkai Zhou, Fan Wang
Abstract: Video try-on replaces clothing in videos with target garments. Existing methods struggle to generate high-quality and temporally consistent results when handling complex clothing patterns and diverse body poses. We present 3DV-TON, a novel diffusion-based framework for generating high-fidelity and temporally consistent video try-on results. Our approach employs generated animatable textured 3D meshes as explicit frame-level guidance, alleviating the issue of models over-focusing on appearance fidelity at the expanse of motion coherence. This is achieved by enabling direct reference to consistent garment texture movements throughout video sequences. The proposed method features an adaptive pipeline for generating dynamic 3D guidance: (1) selecting a keyframe for initial 2D image try-on, followed by (2) reconstructing and animating a textured 3D mesh synchronized with original video poses. We further introduce a robust rectangular masking strategy that successfully mitigates artifact propagation caused by leaking clothing information during dynamic human and garment movements. To advance video try-on research, we introduce HR-VVT, a high-resolution benchmark dataset containing 130 videos with diverse clothing types and scenarios. Quantitative and qualitative results demonstrate our superior performance over existing methods. The project page is at this link https://2y7c3.github.io/3DV-TON/
Authors: Tiancheng Gu, Kaicheng Yang, Ziyong Feng, Xingjun Wang, Yanzhao Zhang, Dingkun Long, Yingda Chen, Weidong Cai, Jiankang Deng
Abstract: The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key limitations: (1) text token truncation, (2) isolated image-text encoding, and (3) deficient compositionality due to bag-of-words behavior. While recent Multimodal Large Language Models (MLLMs) have demonstrated significant advances in generalized vision-language understanding, their potential for learning transferable multimodal representations remains underexplored.In this work, we present UniME (Universal Multimodal Embedding), a novel two-stage framework that leverages MLLMs to learn discriminative representations for diverse downstream tasks. In the first stage, we perform textual discriminative knowledge distillation from a powerful LLM-based teacher model to enhance the embedding capability of the MLLM\'s language component. In the second stage, we introduce hard negative enhanced instruction tuning to further advance discriminative representation learning. Specifically, we initially mitigate false negative contamination and then sample multiple hard negatives per instance within each batch, forcing the model to focus on challenging samples. This approach not only improves discriminative power but also enhances instruction-following ability in downstream tasks. We conduct extensive experiments on the MMEB benchmark and multiple retrieval tasks, including short and long caption retrieval and compositional retrieval. Results demonstrate that UniME achieves consistent performance improvement across all tasks, exhibiting superior discriminative and compositional capabilities.
Authors: Mingxuan Wu, Huang Huang, Justin Kerr, Chung Min Kim, Anthony Zhang, Brent Yi, Angjoo Kanazawa
Abstract: Humans can resort to long-form inspection to build intuition on predicting the 3D configurations of unseen objects. The more we observe the object motion, the better we get at predicting its 3D state immediately. Existing systems either optimize underlying representations from multi-view observations or train a feed-forward predictor from supervised datasets. We introduce Predict-Optimize-Distill (POD), a self-improving framework that interleaves prediction and optimization in a mutually reinforcing cycle to achieve better 4D object understanding with increasing observation time. Given a multi-view object scan and a long-form monocular video of human-object interaction, POD iteratively trains a neural network to predict local part poses from RGB frames, uses this predictor to initialize a global optimization which refines output poses through inverse rendering, then finally distills the results of optimization back into the model by generating synthetic self-labeled training data from novel viewpoints. Each iteration improves both the predictive model and the optimized motion trajectory, creating a virtuous cycle that bootstraps its own training data to learn about the pose configurations of an object. We also introduce a quasi-multiview mining strategy for reducing depth ambiguity by leveraging long video. We evaluate POD on 14 real-world and 5 synthetic objects with various joint types, including revolute and prismatic joints as well as multi-body configurations where parts detach or reattach independently. POD demonstrates significant improvement over a pure optimization baseline which gets stuck in local minima, particularly for longer videos. We also find that POD's performance improves with both video length and successive iterations of the self-improving cycle, highlighting its ability to scale performance with additional observations and looped refinement.
Authors: De-An Huang, Subhashree Radhakrishnan, Zhiding Yu, Jan Kautz
Abstract: There has been impressive progress in Large Multimodal Models (LMMs). Recent works extend these models to long inputs, including multi-page documents and long videos. However, the model size and performance of these long context models are still limited due to the computational cost in both training and inference. In this work, we explore an orthogonal direction and process long inputs without long context LMMs. We propose Frame Selection Augmented Generation (FRAG), where the model first selects relevant frames within the input, and then only generates the final outputs based on the selected frames. The core of the selection process is done by scoring each frame independently, which does not require long context processing. The frames with the highest scores are then selected by a simple Top-K selection. We show that this frustratingly simple framework is applicable to both long videos and multi-page documents using existing LMMs without any fine-tuning. We consider two models, LLaVA-OneVision and InternVL2, in our experiments and show that FRAG consistently improves the performance and achieves state-of-the-art performances for both long video and long document understanding. For videos, FRAG substantially improves InternVL2-76B by 5.8% on MLVU and 3.7% on Video-MME. For documents, FRAG achieves over 20% improvements on MP-DocVQA compared with recent LMMs specialized in long document understanding. Code is available at: https://github.com/NVlabs/FRAG
Authors: Zhiying Li, Yeying Jin, Fan Shen, Zhi Liu, Weibin Chen, Pengju Zhang, Xiaomei Zhang, Boyu Chen, Michael Shen, Kejian Wu, Zhaoxin Fan, Jin Dong
Abstract: Expressive human pose and shape estimation (EHPS) is crucial for digital human generation, especially in applications like live streaming. While existing research primarily focuses on reducing estimation errors, it largely neglects robustness and security aspects, leaving these systems vulnerable to adversarial attacks. To address this significant challenge, we propose the \textbf{Tangible Attack (TBA)}, a novel framework designed to generate adversarial examples capable of effectively compromising any digital human generation model. Our approach introduces a \textbf{Dual Heterogeneous Noise Generator (DHNG)}, which leverages Variational Autoencoders (VAE) and ControlNet to produce diverse, targeted noise tailored to the original image features. Additionally, we design a custom \textbf{adversarial loss function} to optimize the noise, ensuring both high controllability and potent disruption. By iteratively refining the adversarial sample through multi-gradient signals from both the noise and the state-of-the-art EHPS model, TBA substantially improves the effectiveness of adversarial attacks. Extensive experiments demonstrate TBA's superiority, achieving a remarkable 41.0\% increase in estimation error, with an average improvement of approximately 17.0\%. These findings expose significant security vulnerabilities in current EHPS models and highlight the need for stronger defenses in digital human generation systems.
Authors: Weiran Pan, Wei Wei, Feida Zhu, Yong Deng
Abstract: We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently difficult for the model to learn and can exhibit high loss similar to mislabeled samples in the early stages of training. Consequently, setting a threshold on per-sample loss to select correct labels results in a trade-off between precision and recall in sample selection: a lower threshold may miss many correctly labeled hard-to-learn samples (low recall), while a higher threshold may include many mislabeled samples (low precision). To address this issue, our goal is to accurately distinguish correctly labeled yet hard-to-learn samples from mislabeled ones, thus alleviating the trade-off dilemma. We achieve this by considering the trends in model prediction confidence rather than relying solely on loss values. Empirical observations show that only for correctly labeled samples, the model's prediction confidence for the annotated labels typically increases faster than for any other classes. Based on this insight, we propose tracking the confidence gaps between the annotated labels and other classes during training and evaluating their trends using the Mann-Kendall Test. A sample is considered potentially correctly labeled if all its confidence gaps tend to increase. Our method functions as a plug-and-play component that can be seamlessly integrated into existing sample selection techniques. Experiments on several standard benchmarks and real-world datasets demonstrate that our method enhances the performance of existing methods for learning with noisy labels.
Authors: Aviv Slobodkin, Hagai Taitelbaum, Yonatan Bitton, Brian Gordon, Michal Sokolik, Nitzan Bitton Guetta, Almog Gueta, Royi Rassin, Itay Laish, Dani Lischinski, Idan Szpektor
Abstract: Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability -- ranging from enhanced personalization in image generation to consistent character representation in video rendering -- progress in this field is limited by the lack of reliable automatic evaluation. Existing methods either assess only one aspect of the task (i.e., textual alignment or subject preservation), misalign with human judgments, or rely on costly API-based evaluation. To address this, we introduce RefVNLI, a cost-effective metric that evaluates both textual alignment and subject preservation in a single prediction. Trained on a large-scale dataset derived from video-reasoning benchmarks and image perturbations, RefVNLI outperforms or matches existing baselines across multiple benchmarks and subject categories (e.g., \emph{Animal}, \emph{Object}), achieving up to 6.4-point gains in textual alignment and 8.5-point gains in subject consistency. It also excels with lesser-known concepts, aligning with human preferences at over 87\% accuracy.
Authors: Zihan Cheng, Jintao Guo, Jian Zhang, Lei Qi, Luping Zhou, Yinghuan Shi, Yang Gao
Abstract: To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen target domains. Existing DG methods are mainly based on CNN or ViT architectures. Recently, advanced state space models, represented by Mamba, have shown promising results in various supervised medical image segmentation. The success of Mamba is primarily owing to its ability to capture long-range dependencies while keeping linear complexity with input sequence length, making it a promising alternative to CNNs and ViTs. Inspired by the success, in the paper, we explore the potential of the Mamba architecture to address distribution shifts in DG for medical image segmentation. Specifically, we propose a novel Mamba-based framework, Mamba-Sea, incorporating global-to-local sequence augmentation to improve the model's generalizability under domain shift issues. Our Mamba-Sea introduces a global augmentation mechanism designed to simulate potential variations in appearance across different sites, aiming to suppress the model's learning of domain-specific information. At the local level, we propose a sequence-wise augmentation along input sequences, which perturbs the style of tokens within random continuous sub-sequences by modeling and resampling style statistics associated with domain shifts. To our best knowledge, Mamba-Sea is the first work to explore the generalization of Mamba for medical image segmentation, providing an advanced and promising Mamba-based architecture with strong robustness to domain shifts. Remarkably, our proposed method is the first to surpass a Dice coefficient of 90% on the Prostate dataset, which exceeds previous SOTA of 88.61%. The code is available at https://github.com/orange-czh/Mamba-Sea.
Authors: Anyi Xiao, Cihui Yang
Abstract: Table structure recognition aims to parse tables in unstructured data into machine-understandable formats. Recent methods address this problem through a two-stage process or optimized one-stage approaches. However, these methods either require multiple networks to be serially trained and perform more time-consuming sequential decoding, or rely on complex post-processing algorithms to parse the logical structure of tables. They struggle to balance cross-scenario adaptability, robustness, and computational efficiency. In this paper, we propose a one-stage end-to-end table structure parsing network called TableCenterNet. This network unifies the prediction of table spatial and logical structure into a parallel regression task for the first time, and implicitly learns the spatial-logical location mapping laws of cells through a synergistic architecture of shared feature extraction layers and task-specific decoding. Compared with two-stage methods, our method is easier to train and faster to infer. Experiments on benchmark datasets show that TableCenterNet can effectively parse table structures in diverse scenarios and achieve state-of-the-art performance on the TableGraph-24k dataset. Code is available at https://github.com/dreamy-xay/TableCenterNet.
Authors: Junyan Zhang, Yan Li, Mengxiao Geng, Liu Shi, Qiegen Liu
Abstract: Image inpainting is a technique used to restore missing or damaged regions of an image. Traditional methods primarily utilize information from adjacent pixels for reconstructing missing areas, while they struggle to preserve complex details and structures. Simultaneously, models based on deep learning necessitate substantial amounts of training data. To address this challenge, an encoding strategy-inspired diffusion model with few-shot learning for color image inpainting is proposed in this paper. The main idea of this novel encoding strategy is the deployment of a "virtual mask" to construct high-dimensional objects through mutual perturbations between channels. This approach enables the diffusion model to capture diverse image representations and detailed features from limited training samples. Moreover, the encoding strategy leverages redundancy between channels, integrates with low-rank methods during iterative inpainting, and incorporates the diffusion model to achieve accurate information output. Experimental results indicate that our method exceeds current techniques in quantitative metrics, and the reconstructed images quality has been improved in aspects of texture and structural integrity, leading to more precise and coherent results.
Authors: Paul Grimal, Herv\'e Le Borgne, Olivier Ferret
Abstract: Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the signal at critical denoising steps, optimizing image generation based on input semantics. Our approach addresses the shortcomings of early-stage signal modifications, demonstrating that adjustments made at later stages yield superior results. We conduct extensive experiments to validate the effectiveness of our method in producing semantically aligned images on Diffusion and Flow Matching model, achieving state-of-the-art performance. Our results highlight the importance of a judicious choice of sampling stage to improve performance and overall image alignment.
Authors: Ahmadreza Shateri, Negar Nourani, Morteza Dorrigiv, Hamid Nasiri
Abstract: The recent global spread of monkeypox, particularly in regions where it has not historically been prevalent, has raised significant public health concerns. Early and accurate diagnosis is critical for effective disease management and control. In response, this study proposes a novel deep learning-based framework for the automated detection of monkeypox from skin lesion images, leveraging the power of transfer learning, dimensionality reduction, and advanced machine learning techniques. We utilize the newly developed Monkeypox Skin Lesion Dataset (MSLD), which includes images of monkeypox, chickenpox, and measles, to train and evaluate our models. The proposed framework employs the Xception architecture for deep feature extraction, followed by Principal Component Analysis (PCA) for dimensionality reduction, and the Natural Gradient Boosting (NGBoost) algorithm for classification. To optimize the model's performance and generalization, we introduce the African Vultures Optimization Algorithm (AVOA) for hyperparameter tuning, ensuring efficient exploration of the parameter space. Our results demonstrate that the proposed AVOA-NGBoost model achieves state-of-the-art performance, with an accuracy of 97.53%, F1-score of 97.72% and an AUC of 97.47%. Additionally, we enhance model interpretability using Grad-CAM and LIME techniques, providing insights into the decision-making process and highlighting key features influencing classification. This framework offers a highly precise and efficient diagnostic tool, potentially aiding healthcare providers in early detection and diagnosis, particularly in resource-constrained environments.
Authors: Keyang Ye, Tianjia Shao, Kun Zhou
Abstract: We introduce Gaussian-enhanced Surfels (GESs), a bi-scale representation for radiance field rendering, wherein a set of 2D opaque surfels with view-dependent colors represent the coarse-scale geometry and appearance of scenes, and a few 3D Gaussians surrounding the surfels supplement fine-scale appearance details. The rendering with GESs consists of two passes -- surfels are first rasterized through a standard graphics pipeline to produce depth and color maps, and then Gaussians are splatted with depth testing and color accumulation on each pixel order independently. The optimization of GESs from multi-view images is performed through an elaborate coarse-to-fine procedure, faithfully capturing rich scene appearance. The entirely sorting-free rendering of GESs not only achieves very fast rates, but also produces view-consistent images, successfully avoiding popping artifacts under view changes. The basic GES representation can be easily extended to achieve anti-aliasing in rendering (Mip-GES), boosted rendering speeds (Speedy-GES) and compact storage (Compact-GES), and reconstruct better scene geometries by replacing 3D Gaussians with 2D Gaussians (2D-GES). Experimental results show that GESs advance the state-of-the-arts as a compelling representation for ultra-fast high-fidelity radiance field rendering.
Authors: Jiaqi Deng, Zonghan Wu, Huan Huo, Guandong Xu
Abstract: Knowledge-based Vision Question Answering (KB-VQA) extends general Vision Question Answering (VQA) by not only requiring the understanding of visual and textual inputs but also extensive range of knowledge, enabling significant advancements across various real-world applications. KB-VQA introduces unique challenges, including the alignment of heterogeneous information from diverse modalities and sources, the retrieval of relevant knowledge from noisy or large-scale repositories, and the execution of complex reasoning to infer answers from the combined context. With the advancement of Large Language Models (LLMs), KB-VQA systems have also undergone a notable transformation, where LLMs serve as powerful knowledge repositories, retrieval-augmented generators and strong reasoners. Despite substantial progress, no comprehensive survey currently exists that systematically organizes and reviews the existing KB-VQA methods. This survey aims to fill this gap by establishing a structured taxonomy of KB-VQA approaches, and categorizing the systems into main stages: knowledge representation, knowledge retrieval, and knowledge reasoning. By exploring various knowledge integration techniques and identifying persistent challenges, this work also outlines promising future research directions, providing a foundation for advancing KB-VQA models and their applications.
Authors: Lin Che, Yizi Chen, Tanhua Jin, Martin Raubal, Konrad Schindler, Peter Kiefer
Abstract: Urban land use classification and mapping are critical for urban planning, resource management, and environmental monitoring. Existing remote sensing techniques often lack precision in complex urban environments due to the absence of ground-level details. Unlike aerial perspectives, street view images provide a ground-level view that captures more human and social activities relevant to land use in complex urban scenes. Existing street view-based methods primarily rely on supervised classification, which is challenged by the scarcity of high-quality labeled data and the difficulty of generalizing across diverse urban landscapes. This study introduces an unsupervised contrastive clustering model for street view images with a built-in geographical prior, to enhance clustering performance. When combined with a simple visual assignment of the clusters, our approach offers a flexible and customizable solution to land use mapping, tailored to the specific needs of urban planners. We experimentally show that our method can generate land use maps from geotagged street view image datasets of two cities. As our methodology relies on the universal spatial coherence of geospatial data ("Tobler's law"), it can be adapted to various settings where street view images are available, to enable scalable, unsupervised land use mapping and updating. The code will be available at https://github.com/lin102/CCGP.
Authors: Zebo Huang, Yinghui Wang
Abstract: We propose a self-supervised monocular depth estimation network tailored for endoscopic scenes, aiming to infer depth within the gastrointestinal tract from monocular images. Existing methods, though accurate, typically assume consistent illumination, which is often violated due to dynamic lighting and occlusions caused by GI motility. These variations lead to incorrect geometric interpretations and unreliable self-supervised signals, degrading depth reconstruction quality. To address this, we introduce an occlusion-aware self-supervised framework. First, we incorporate an occlusion mask for data augmentation, generating pseudo-labels by simulating viewpoint-dependent occlusion scenarios. This enhances the model's ability to learn robust depth features under partial visibility. Second, we leverage semantic segmentation guided by non-negative matrix factorization, clustering convolutional activations to generate pseudo-labels in texture-deprived regions, thereby improving segmentation accuracy and mitigating information loss from lighting changes. Experimental results on the SCARED dataset show that our method achieves state-of-the-art performance in self-supervised depth estimation. Additionally, evaluations on the Endo-SLAM and SERV-CT datasets demonstrate strong generalization across diverse endoscopic environments.
Authors: Zhaofeng Si, Siwei Lyu
Abstract: An intriguing phenomenon about JPEG compression has been observed since two decades ago- after repeating JPEG compression and decompression, it leads to a stable image that does not change anymore, which is a fixed point. In this work, we prove the existence of fixed points in the essential JPEG procedures. We analyze JPEG compression and decompression processes, revealing the existence of fixed points that can be reached within a few iterations. These fixed points are diverse and preserve the image's visual quality, ensuring minimal distortion. This result is used to develop a method to create a tamper-evident image from the original authentic image, which can expose tampering operations by showing deviations from the fixed point image.
Authors: Boyue Xu, Yi Xu, Ruichao Hou, Jia Bei, Tongwei Ren, Gangshan Wu
Abstract: The integration of dual-modal features has been pivotal in advancing RGB-Depth (RGB-D) tracking. However, current trackers are less efficient and focus solely on single-level features, resulting in weaker robustness in fusion and slower speeds that fail to meet the demands of real-world applications. In this paper, we introduce a novel network, denoted as HMAD (Hierarchical Modality Aggregation and Distribution), which addresses these challenges. HMAD leverages the distinct feature representation strengths of RGB and depth modalities, giving prominence to a hierarchical approach for feature distribution and fusion, thereby enhancing the robustness of RGB-D tracking. Experimental results on various RGB-D datasets demonstrate that HMAD achieves state-of-the-art performance. Moreover, real-world experiments further validate HMAD's capacity to effectively handle a spectrum of tracking challenges in real-time scenarios.
Authors: Fengchun Liu, Tong Zhang, Chunying Zhang
Abstract: Aiming at the problems of poor quality of steganographic images and slow network convergence of image steganography models based on deep learning, this paper proposes a Steganography Curriculum Learning training strategy (STCL) for deep learning image steganography models. So that only easy images are selected for training when the model has poor fitting ability at the initial stage, and gradually expand to more difficult images, the strategy includes a difficulty evaluation strategy based on the teacher model and an knee point-based training scheduling strategy. Firstly, multiple teacher models are trained, and the consistency of the quality of steganographic images under multiple teacher models is used as the difficulty score to construct the training subsets from easy to difficult. Secondly, a training control strategy based on knee points is proposed to reduce the possibility of overfitting on small training sets and accelerate the training process. Experimental results on three large public datasets, ALASKA2, VOC2012 and ImageNet, show that the proposed image steganography scheme is able to improve the model performance under multiple algorithmic frameworks, which not only has a high PSNR, SSIM score, and decoding accuracy, but also the steganographic images generated by the model under the training of the STCL strategy have a low steganography analysis scores. You can find our code at \href{https://github.com/chaos-boops/STCL}{https://github.com/chaos-boops/STCL}.
URLs: https://github.com/chaos-boops/STCL, https://github.com/chaos-boops/STCL
Authors: Catarina P. Coutinho, Aneeqa Merhab, Janko Petkovic, Ferdinando Zanchetta, Rita Fioresi
Abstract: We exploit the mathematical modeling of the visual cortex mechanism for border completion to define custom filters for CNNs. We see a consistent improvement in performance, particularly in accuracy, when our modified LeNet 5 is tested with occluded MNIST images.
Authors: Ashish Singh, Michael J. Jones, Kuan-Chuan Peng, Anoop Cherian, Moitreya Chatterjee, Erik Learned-Miller
Abstract: Our work addresses the problem of learning to localize objects in an open-world setting, i.e., given the bounding box information of a limited number of object classes during training, the goal is to localize all objects, belonging to both the training and unseen classes in an image, during inference. Towards this end, recent work in this area has focused on improving the characterization of objects either explicitly by proposing new objective functions (localization quality) or implicitly using object-centric auxiliary-information, such as depth information, pixel/region affinity map etc. In this work, we address this problem by incorporating background information to guide the learning of the notion of objectness. Specifically, we propose a novel framework to discover background regions in an image and train an object proposal network to not detect any objects in these regions. We formulate the background discovery task as that of identifying image regions that are not discriminative, i.e., those that are redundant and constitute low information content. We conduct experiments on standard benchmarks to showcase the effectiveness of our proposed approach and observe significant improvements over the previous state-of-the-art approaches for this task.
Authors: Vojtech Panek, Qunjie Zhou, Yaqing Ding, S\'ergio Agostinho, Zuzana Kukelova, Torsten Sattler, Laura Leal-Taix\'e
Abstract: Visual localization algorithms, i.e., methods that estimate the camera pose of a query image in a known scene, are core components of many applications, including self-driving cars and augmented / mixed reality systems. State-of-the-art visual localization algorithms are structure-based, i.e., they store a 3D model of the scene and use 2D-3D correspondences between the query image and 3D points in the model for camera pose estimation. While such approaches are highly accurate, they are also rather inflexible when it comes to adjusting the underlying 3D model after changes in the scene. Structureless localization approaches represent the scene as a database of images with known poses and thus offer a much more flexible representation that can be easily updated by adding or removing images. Although there is a large amount of literature on structure-based approaches, there is significantly less work on structureless methods. Hence, this paper is dedicated to providing the, to the best of our knowledge, first comprehensive discussion and comparison of structureless methods. Extensive experiments show that approaches that use a higher degree of classical geometric reasoning generally achieve higher pose accuracy. In particular, approaches based on classical absolute or semi-generalized relative pose estimation outperform very recent methods based on pose regression by a wide margin. Compared with state-of-the-art structure-based approaches, the flexibility of structureless methods comes at the cost of (slightly) lower pose accuracy, indicating an interesting direction for future work.
Authors: Steve G\"oring
Abstract: A brief overview of CLIPSE, a self-hosted image search engine with the main application of research, is provided. In general, CLIPSE uses CLIP embeddings to process the images and also the text queries. The overall framework is designed with simplicity to enable easy extension and usage. Two benchmark scenarios are described and evaluated, covering indexing and querying time. It is shown that CLIPSE is capable of handling smaller datasets; for larger datasets, a distributed approach with several instances should be considered.
Authors: Lutao Jiang, Jiantao Lin, Kanghao Chen, Wenhang Ge, Xin Yang, Yifan Jiang, Yuanhuiyi Lyu, Xu Zheng, Yingcong Chen
Abstract: With the advent of large-scale 3D datasets, feed-forward 3D generative models, such as the Large Reconstruction Model (LRM), have gained significant attention and achieved remarkable success. However, we observe that RGB images often lead to conflicting training objectives and lack the necessary clarity for geometry reconstruction. In this paper, we revisit the inductive biases associated with mesh reconstruction and introduce DiMeR, a novel disentangled dual-stream feed-forward model for sparse-view mesh reconstruction. The key idea is to disentangle both the input and framework into geometry and texture parts, thereby reducing the training difficulty for each part according to the Principle of Occam's Razor. Given that normal maps are strictly consistent with geometry and accurately capture surface variations, we utilize normal maps as exclusive input for the geometry branch to reduce the complexity between the network's input and output. Moreover, we improve the mesh extraction algorithm to introduce 3D ground truth supervision. As for texture branch, we use RGB images as input to obtain the textured mesh. Overall, DiMeR demonstrates robust capabilities across various tasks, including sparse-view reconstruction, single-image-to-3D, and text-to-3D. Numerous experiments show that DiMeR significantly outperforms previous methods, achieving over 30% improvement in Chamfer Distance on the GSO and OmniObject3D dataset.
Authors: Alp\'ar Cseke, Shashank Tripathi, Sai Kumar Dwivedi, Arjun Lakshmipathy, Agniv Chatterjee, Michael J. Black, Dimitrios Tzionas
Abstract: Recovering 3D Human-Object Interaction (HOI) from single color images is challenging due to depth ambiguities, occlusions, and the huge variation in object shape and appearance. Thus, past work requires controlled settings such as known object shapes and contacts, and tackles only limited object classes. Instead, we need methods that generalize to natural images and novel object classes. We tackle this in two main ways: (1) We collect PICO-db, a new dataset of natural images uniquely paired with dense 3D contact on both body and object meshes. To this end, we use images from the recent DAMON dataset that are paired with contacts, but these contacts are only annotated on a canonical 3D body. In contrast, we seek contact labels on both the body and the object. To infer these given an image, we retrieve an appropriate 3D object mesh from a database by leveraging vision foundation models. Then, we project DAMON's body contact patches onto the object via a novel method needing only 2 clicks per patch. This minimal human input establishes rich contact correspondences between bodies and objects. (2) We exploit our new dataset of contact correspondences in a novel render-and-compare fitting method, called PICO-fit, to recover 3D body and object meshes in interaction. PICO-fit infers contact for the SMPL-X body, retrieves a likely 3D object mesh and contact from PICO-db for that object, and uses the contact to iteratively fit the 3D body and object meshes to image evidence via optimization. Uniquely, PICO-fit works well for many object categories that no existing method can tackle. This is crucial to enable HOI understanding to scale in the wild. Our data and code are available at https://pico.is.tue.mpg.de.
Authors: Ghazal Kaviani, Yavuz Yarici, Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib, Mashhour Solh, Ameya Patil
Abstract: Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in real-world settings. DARai consists of continuous scripted and unscripted recordings of 50 participants in 10 different environments, totaling over 200 hours of data from 20 sensors including multiple camera views, depth and radar sensors, wearable inertial measurement units (IMUs), electromyography (EMG), insole pressure sensors, biomonitor sensors, and gaze tracker. To capture the complexity in human activities, DARai is annotated at three levels of hierarchy: (i) high-level activities (L1) that are independent tasks, (ii) lower-level actions (L2) that are patterns shared between activities, and (iii) fine-grained procedures (L3) that detail the exact execution steps for actions. The dataset annotations and recordings are designed so that 22.7% of L2 actions are shared between L1 activities and 14.2% of L3 procedures are shared between L2 actions. The overlap and unscripted nature of DARai allows counterfactual activities in the dataset. Experiments with various machine learning models showcase the value of DARai in uncovering important challenges in human-centered applications. Specifically, we conduct unimodal and multimodal sensor fusion experiments for recognition, temporal localization, and future action anticipation across all hierarchical annotation levels. To highlight the limitations of individual sensors, we also conduct domain-variant experiments that are enabled by DARai's multi-sensor and counterfactual activity design setup. The code, documentation, and dataset are available at the dedicated DARai website: https://alregib.ece.gatech.edu/software-and-datasets/darai-daily-activity-recordings-for-artificial-intelligence-and-machine-learning/
Authors: Zhuo He, Paul Henderson, Nicolas Pugeault
Abstract: StyleGAN has demonstrated the ability of GANs to synthesize highly-realistic faces of imaginary people from random noise. One limitation of GAN-based image generation is the difficulty of controlling the features of the generated image, due to the strong entanglement of the low-dimensional latent space. Previous work that aimed to control StyleGAN with image or text prompts modulated sampling in W latent space, which is more expressive than Z latent space. However, W space still has restricted expressivity since it does not control the feature synthesis directly; also the feature embedding in W space requires a pre-training process to reconstruct the style signal, limiting its application. This paper introduces the concept of "generative fields" to explain the hierarchical feature synthesis in StyleGAN, inspired by the receptive fields of convolution neural networks (CNNs). Additionally, we propose a new image editing pipeline for StyleGAN using generative field theory and the channel-wise style latent space S, utilizing the intrinsic structural feature of CNNs to achieve disentangled control of feature synthesis at synthesis time.
Authors: Zhanwen Liu, Sai Zhou, Yuchao Dai, Yang Wang, Yisheng An, Xiangmo Zhao
Abstract: All-in-One image restoration aims to address multiple image degradation problems using a single model, significantly reducing training costs and deployment complexity compared to traditional methods that design dedicated models for each degradation type. Existing approaches typically rely on Degradation-specific models or coarse-grained degradation prompts to guide image restoration. However, they lack fine-grained modeling of degradation information and face limitations in balancing multi-task conflicts. To overcome these limitations, we propose DPMambaIR, a novel All-in-One image restoration framework. By integrating a Degradation-Aware Prompt State Space Model (DP-SSM) and a High-Frequency Enhancement Block (HEB), DPMambaIR enables fine-grained modeling of complex degradation information and efficient global integration, while mitigating the loss of high-frequency details caused by task competition. Specifically, the DP-SSM utilizes a pre-trained degradation extractor to capture fine-grained degradation features and dynamically incorporates them into the state space modeling process, enhancing the model's adaptability to diverse degradation types. Concurrently, the HEB supplements high-frequency information, effectively addressing the loss of critical details, such as edges and textures, in multi-task image restoration scenarios. Extensive experiments on a mixed dataset containing seven degradation types show that DPMambaIR achieves the best performance, with 27.69dB and 0.893 in PSNR and SSIM, respectively. These results highlight the potential and superiority of DPMambaIR as a unified solution for All-in-One image restoration.
Authors: Akhil Padmanabha, Saravanan Govindarajan, Hwanmun Kim, Sergio Ortiz, Rahul Rajan, Doruk Senkal, Sneha Kadetotad
Abstract: Human activity recognition (HAR) on smartglasses has various use cases, including health/fitness tracking and input for context-aware AI assistants. However, current approaches for egocentric activity recognition suffer from low performance or are resource-intensive. In this work, we introduce a resource (memory, compute, power, sample) efficient machine learning algorithm, EgoCHARM, for recognizing both high level and low level activities using a single egocentric (head-mounted) Inertial Measurement Unit (IMU). Our hierarchical algorithm employs a semi-supervised learning strategy, requiring primarily high level activity labels for training, to learn generalizable low level motion embeddings that can be effectively utilized for low level activity recognition. We evaluate our method on 9 high level and 3 low level activities achieving 0.826 and 0.855 F1 scores on high level and low level activity recognition respectively, with just 63k high level and 22k low level model parameters, allowing the low level encoder to be deployed directly on current IMU chips with compute. Lastly, we present results and insights from a sensitivity analysis and highlight the opportunities and limitations of activity recognition using egocentric IMUs.
Authors: Shiyu Liu, Yucheng Han, Peng Xing, Fukun Yin, Rui Wang, Wei Cheng, Jiaqi Liao, Yingming Wang, Honghao Fu, Chunrui Han, Guopeng Li, Yuang Peng, Quan Sun, Jingwei Wu, Yan Cai, Zheng Ge, Ranchen Ming, Lei Xia, Xianfang Zeng, Yibo Zhu, Binxing Jiao, Xiangyu Zhang, Gang Yu, Daxin Jiang
Abstract: In recent years, image editing models have witnessed remarkable and rapid development. The recent unveiling of cutting-edge multimodal models such as GPT-4o and Gemini2 Flash has introduced highly promising image editing capabilities. These models demonstrate an impressive aptitude for fulfilling a vast majority of user-driven editing requirements, marking a significant advancement in the field of image manipulation. However, there is still a large gap between the open-source algorithm with these closed-source models. Thus, in this paper, we aim to release a state-of-the-art image editing model, called Step1X-Edit, which can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash. More specifically, we adopt the Multimodal LLM to process the reference image and the user's editing instruction. A latent embedding has been extracted and integrated with a diffusion image decoder to obtain the target image. To train the model, we build a data generation pipeline to produce a high-quality dataset. For evaluation, we develop the GEdit-Bench, a novel benchmark rooted in real-world user instructions. Experimental results on GEdit-Bench demonstrate that Step1X-Edit outperforms existing open-source baselines by a substantial margin and approaches the performance of leading proprietary models, thereby making significant contributions to the field of image editing.
Authors: Anton Obukhov, Matteo Poggi, Fabio Tosi, Ripudaman Singh Arora, Jaime Spencer, Chris Russell, Simon Hadfield, Richard Bowden, Shuaihang Wang, Zhenxin Ma, Weijie Chen, Baobei Xu, Fengyu Sun, Di Xie, Jiang Zhu, Mykola Lavreniuk, Haining Guan, Qun Wu, Yupei Zeng, Chao Lu, Huanran Wang, Guangyuan Zhou, Haotian Zhang, Jianxiong Wang, Qiang Rao, Chunjie Wang, Xiao Liu, Zhiqiang Lou, Hualie Jiang, Yihao Chen, Rui Xu, Minglang Tan, Zihan Qin, Yifan Mao, Jiayang Liu, Jialei Xu, Yifan Yang, Wenbo Zhao, Junjun Jiang, Xianming Liu, Mingshuai Zhao, Anlong Ming, Wu Chen, Feng Xue, Mengying Yu, Shida Gao, Xiangfeng Wang, Gbenga Omotara, Ramy Farag, Jacket Demby, Seyed Mohamad Ali Tousi, Guilherme N DeSouza, Tuan-Anh Yang, Minh-Quang Nguyen, Thien-Phuc Tran, Albert Luginov, Muhammad Shahzad
Abstract: This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.
Authors: Chris Rockwell, Joseph Tung, Tsung-Yi Lin, Ming-Yu Liu, David F. Fouhey, Chen-Hsuan Lin
Abstract: Annotating camera poses on dynamic Internet videos at scale is critical for advancing fields like realistic video generation and simulation. However, collecting such a dataset is difficult, as most Internet videos are unsuitable for pose estimation. Furthermore, annotating dynamic Internet videos present significant challenges even for state-of-theart methods. In this paper, we introduce DynPose-100K, a large-scale dataset of dynamic Internet videos annotated with camera poses. Our collection pipeline addresses filtering using a carefully combined set of task-specific and generalist models. For pose estimation, we combine the latest techniques of point tracking, dynamic masking, and structure-from-motion to achieve improvements over the state-of-the-art approaches. Our analysis and experiments demonstrate that DynPose-100K is both large-scale and diverse across several key attributes, opening up avenues for advancements in various downstream applications.
Authors: Xu Ma, Peize Sun, Haoyu Ma, Hao Tang, Chih-Yao Ma, Jialiang Wang, Kunpeng Li, Xiaoliang Dai, Yujun Shi, Xuan Ju, Yushi Hu, Artsiom Sanakoyeu, Felix Juefei-Xu, Ji Hou, Junjiao Tian, Tao Xu, Tingbo Hou, Yen-Cheng Liu, Zecheng He, Zijian He, Matt Feiszli, Peizhao Zhang, Peter Vajda, Sam Tsai, Yun Fu
Abstract: Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image tokens required for AR models, which constrains both training and inference efficiency, as well as image resolution. To address this, we present Token-Shuffle, a novel yet simple method that reduces the number of image tokens in Transformer. Our key insight is the dimensional redundancy of visual vocabularies in Multimodal Large Language Models (MLLMs), where low-dimensional visual codes from visual encoder are directly mapped to high-dimensional language vocabularies. Leveraging this, we consider two key operations: token-shuffle, which merges spatially local tokens along channel dimension to decrease the input token number, and token-unshuffle, which untangles the inferred tokens after Transformer blocks to restore the spatial arrangement for output. Jointly training with textual prompts, our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis in a unified next-token prediction way while maintaining efficient training and inference. For the first time, we push the boundary of AR text-to-image generation to a resolution of 2048x2048 with gratifying generation performance. In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15. Exhaustive large-scale human evaluations also demonstrate our prominent image generation ability in terms of text-alignment, visual flaw, and visual appearance. We hope that Token-Shuffle can serve as a foundational design for efficient high-resolution image generation within MLLMs.
Authors: Tetiana Martyniuk, Gilles Puy, Alexandre Boulch, Renaud Marlet, Raoul de Charette
Abstract: Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM .
Authors: Yusheng Zhao, Junyu Luo, Xiao Luo, Weizhi Zhang, Zhiping Xiao, Wei Ju, Philip S. Yu, Ming Zhang
Abstract: Multi-modal large language models (MLLMs) have recently achieved great success in processing and understanding information from diverse modalities (e.g., text, audio, and visual signals). Despite their growing popularity, there remains a lack of comprehensive evaluation measuring the audio-visual capabilities of these models, especially in diverse scenarios (e.g., distribution shifts and adversarial attacks). In this paper, we present a multifaceted evaluation of the audio-visual capability of MLLMs, focusing on four key dimensions: effectiveness, efficiency, generalizability, and robustness. Through extensive experiments, we find that MLLMs exhibit strong zero-shot and few-shot generalization abilities, enabling them to achieve great performance with limited data. However, their success relies heavily on the vision modality, which impairs performance when visual input is corrupted or missing. Additionally, while MLLMs are susceptible to adversarial samples, they demonstrate greater robustness compared to traditional models. The experimental results and our findings provide insights into the audio-visual capabilities of MLLMs, highlighting areas for improvement and offering guidance for future research.
Authors: Drew Linsley, Pinyuan Feng, Thomas Serre
Abstract: Deep neural networks (DNNs) once showed increasing alignment with primate neural responses as they improved on computer vision benchmarks. This trend raised the exciting possibility that better models of biological vision would come as a byproduct of the deep learning revolution in artificial intelligence. However, the trend has reversed over recent years as DNNs have scaled to human or superhuman recognition accuracy, a divergence that may stem from modern DNNs learning to rely on different visual features than primates to solve tasks. Where will better computational models of biological vision come from? We propose that vision science must break from artificial intelligence to develop algorithms that are designed with biological visual systems in mind instead of internet data benchmarks. We predict that the next generation of deep learning models of biological vision will be trained with data diets, training routines, and objectives that are closer to those that shape human vision than those that are in use today.
Authors: Shushman Choudhury, Elad Aharoni, Chandrakumari Suvarna, Iveel Tsogsuren, Abdul Rahman Kreidieh, Chun-Ta Lu, Neha Arora
Abstract: Scalable general-purpose representations of the built environment are crucial for geospatial artificial intelligence applications. This paper introduces S2Vec, a novel self-supervised framework for learning such geospatial embeddings. S2Vec uses the S2 Geometry library to partition large areas into discrete S2 cells, rasterizes built environment feature vectors within cells as images, and applies masked autoencoding on these rasterized images to encode the feature vectors. This approach yields task-agnostic embeddings that capture local feature characteristics and broader spatial relationships. We evaluate S2Vec on three large-scale socioeconomic prediction tasks, showing its competitive performance against state-of-the-art image-based embeddings. We also explore the benefits of combining S2Vec embeddings with image-based embeddings downstream, showing that such multimodal fusion can often improve performance. Our results highlight how S2Vec can learn effective general-purpose geospatial representations and how it can complement other data modalities in geospatial artificial intelligence.
Authors: Hossein Ahmadi, Sajjad Emdadi Mahdimahalleh, Arman Farahat, Banafsheh Saffari
Abstract: The rapid growth of unlabeled time-series data in domains such as wireless communications, radar, biomedical engineering, and the Internet of Things (IoT) has driven advancements in unsupervised learning. This review synthesizes recent progress in applying autoencoders and vision transformers for unsupervised signal analysis, focusing on their architectures, applications, and emerging trends. We explore how these models enable feature extraction, anomaly detection, and classification across diverse signal types, including electrocardiograms, radar waveforms, and IoT sensor data. The review highlights the strengths of hybrid architectures and self-supervised learning, while identifying challenges in interpretability, scalability, and domain generalization. By bridging methodological innovations and practical applications, this work offers a roadmap for developing robust, adaptive models for signal intelligence.
Authors: Hidde Makimei, Shuai Wang, Willem van Peursen
Abstract: The past years witnessed a significant amount of Artificial Intelligence (AI) tools that can generate images from texts. This triggers the discussion of whether AI can generate accurate images using text from the Bible with respect to the corresponding biblical contexts and backgrounds. Despite some existing attempts at a small scale, little work has been done to systematically evaluate these generated images. In this work, we provide a large dataset of over 7K images using biblical text as prompts. These images were evaluated with multiple neural network-based tools on various aspects. We provide an assessment of accuracy and some analysis from the perspective of religion and aesthetics. Finally, we discuss the use of the generated images and reflect on the performance of the AI generators.
Authors: Masoud Tafavvoghi, Lars Ailo Bongo, Andr\'e Berli Delgado, Nikita Shvetsov, Anders Sildnes, Line Moi, Lill-Tove Rasmussen Busund, Kajsa M{\o}llersen
Abstract: In this study, we built an end-to-end tumor-infiltrating lymphocytes (TILs) assessment pipeline within QuPath, demonstrating the potential of easily accessible tools to perform complex tasks in a fully automatic fashion. First, we trained a pixel classifier to segment tumor, tumor-associated stroma, and other tissue compartments in breast cancer H&E-stained whole-slide images (WSI) to isolate tumor-associated stroma for subsequent analysis. Next, we applied a pre-trained StarDist deep learning model in QuPath for cell detection and used the extracted cell features to train a binary classifier distinguishing TILs from other cells. To evaluate our TILs assessment pipeline, we calculated the TIL density in each WSI and categorized them as low, medium, or high TIL levels. Our pipeline was evaluated against pathologist-assigned TIL scores, achieving a Cohen's kappa of 0.71 on the external test set, corroborating previous research findings. These results confirm that existing software can offer a practical solution for the assessment of TILs in H&E-stained WSIs of breast cancer.
Authors: Yu Guo, Zhiqiang Lao, Xiyun Song, Yubin Zhou, Zongfang Lin, Heather Yu
Abstract: Realistic indoor or outdoor image synthesis is a core challenge in computer vision and graphics. The learning-based approach is easy to use but lacks physical consistency, while traditional Physically Based Rendering (PBR) offers high realism but is computationally expensive. Intrinsic image representation offers a well-balanced trade-off, decomposing images into fundamental components (intrinsic channels) such as geometry, materials, and illumination for controllable synthesis. However, existing PBR materials struggle with complex surface models, particularly high-specular and transparent surfaces. In this work, we extend intrinsic image representations to incorporate both reflection and transmission properties, enabling the synthesis of transparent materials such as glass and windows. We propose an explicit intrinsic compositing framework that provides deterministic, interpretable image synthesis. With the Extended PBR (ePBR) Materials, we can effectively edit the materials with precise controls.
Authors: Valentin Langer, Kartikay Tehlan, Thomas Wendler
Abstract: Accurate kinetic analysis of [$^{18}$F]FDG distribution in dynamic positron emission tomography (PET) requires anatomically constrained modelling of image-derived input functions (IDIFs). Traditionally, IDIFs are obtained from the aorta, neglecting anatomical variations and complex vascular contributions. This study proposes a multi-organ segmentation-based approach that integrates IDIFs from the aorta, portal vein, pulmonary artery, and ureters. Using high-resolution CT segmentations of the liver, lungs, kidneys, and bladder, we incorporate organ-specific blood supply sources to improve kinetic modelling. Our method was evaluated on dynamic [$^{18}$F]FDG PET data from nine patients, resulting in a mean squared error (MSE) reduction of $13.39\%$ for the liver and $10.42\%$ for the lungs. These initial results highlight the potential of multiple IDIFs in improving anatomical modelling and fully leveraging dynamic PET imaging. This approach could facilitate the integration of tracer kinetic modelling into clinical routine.
Authors: Kartikay Tehlan, Thomas Wendler
Abstract: Dynamic positron emission tomography (PET) with [$^{18}$F]FDG enables non-invasive quantification of glucose metabolism through kinetic analysis, often modelled by the two-tissue compartment model (TCKM). However, voxel-wise kinetic parameter estimation using conventional methods is computationally intensive and limited by spatial resolution. Deep neural networks (DNNs) offer an alternative but require large training datasets and significant computational resources. To address these limitations, we propose a physiological neural representation based on implicit neural representations (INRs) for personalized kinetic parameter estimation. INRs, which learn continuous functions, allow for efficient, high-resolution parametric imaging with reduced data requirements. Our method also integrates anatomical priors from a 3D CT foundation model to enhance robustness and precision in kinetic modelling. We evaluate our approach on an [$^{18}$F]FDG dynamic PET/CT dataset and compare it to state-of-the-art DNNs. Results demonstrate superior spatial resolution, lower mean-squared error, and improved anatomical consistency, particularly in tumour and highly vascularized regions. Our findings highlight the potential of INRs for personalized, data-efficient tracer kinetic modelling, enabling applications in tumour characterization, segmentation, and prognostic assessment.
Authors: Alberto Fern\'andez-Hern\'andez, Jose I. Mestre, Manuel F. Dolz, Jose Duato, Enrique S. Quintana-Ort\'i
Abstract: We introduce the Overfitting-Underfitting Indicator (OUI), a novel tool for monitoring the training dynamics of Deep Neural Networks (DNNs) and identifying optimal regularization hyperparameters. Specifically, we validate that OUI can effectively guide the selection of the Weight Decay (WD) hyperparameter by indicating whether a model is overfitting or underfitting during training without requiring validation data. Through experiments on DenseNet-BC-100 with CIFAR- 100, EfficientNet-B0 with TinyImageNet and ResNet-34 with ImageNet-1K, we show that maintaining OUI within a prescribed interval correlates strongly with improved generalization and validation scores. Notably, OUI converges significantly faster than traditional metrics such as loss or accuracy, enabling practitioners to identify optimal WD (hyperparameter) values within the early stages of training. By leveraging OUI as a reliable indicator, we can determine early in training whether the chosen WD value leads the model to underfit the training data, overfit, or strike a well-balanced trade-off that maximizes validation scores. This enables more precise WD tuning for optimal performance on the tested datasets and DNNs. All code for reproducing these experiments is available at https://github.com/AlbertoFdezHdez/OUI.
Authors: Mohammad Zarei, Melanie A Jutras, Eliana Evans, Mike Tan, Omid Aaramoon
Abstract: Autonomous Vehicles (AVs) rely on artificial intelligence (AI) to accurately detect objects and interpret their surroundings. However, even when trained using millions of miles of real-world data, AVs are often unable to detect rare failure modes (RFMs). The problem of RFMs is commonly referred to as the "long-tail challenge", due to the distribution of data including many instances that are very rarely seen. In this paper, we present a novel approach that utilizes advanced generative and explainable AI techniques to aid in understanding RFMs. Our methods can be used to enhance the robustness and reliability of AVs when combined with both downstream model training and testing. We extract segmentation masks for objects of interest (e.g., cars) and invert them to create environmental masks. These masks, combined with carefully crafted text prompts, are fed into a custom diffusion model. We leverage the Stable Diffusion inpainting model guided by adversarial noise optimization to generate images containing diverse environments designed to evade object detection models and expose vulnerabilities in AI systems. Finally, we produce natural language descriptions of the generated RFMs that can guide developers and policymakers to improve the safety and reliability of AV systems.
Authors: Md Ashiqur Rahman, Raymond A. Yeh
Abstract: Downsampling layers are crucial building blocks in CNN architectures, which help to increase the receptive field for learning high-level features and reduce the amount of memory/computation in the model. In this work, we study the generalization of the uniform downsampling layer for group equivariant architectures, e.g., G-CNNs. That is, we aim to downsample signals (feature maps) on general finite groups with anti-aliasing. This involves the following: (a) Given a finite group and a downsampling rate, we present an algorithm to form a suitable choice of subgroup. (b) Given a group and a subgroup, we study the notion of bandlimited-ness and propose how to perform anti-aliasing. Notably, our method generalizes the notion of downsampling based on classical sampling theory. When the signal is on a cyclic group, i.e., periodic, our method recovers the standard downsampling of an ideal low-pass filter followed by a subsampling operation. Finally, we conducted experiments on image classification tasks demonstrating that the proposed downsampling operation improves accuracy, better preserves equivariance, and reduces model size when incorporated into G-equivariant networks
Authors: Miaoyun Zhao, Qiang Zhang, Chenrong Li
Abstract: Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. Existing research attributes this issue to group imbalance and addresses it by maximizing group-balanced or worst-group accuracy, which heavily relies on expensive bias annotations. A compromise approach involves predicting bias information using extensively pretrained foundation models, which requires large-scale data and becomes impractical for resource-limited rare domains. To address these challenges, we offer a novel perspective by reframing the spurious correlations as imbalances or mismatches in class-conditional distributions, and propose a simple yet effective robust learning method that eliminates the need for both bias annotations and predictions. With the goal of reducing the mutual information between spurious factors and label information, our method leverages a sample reweighting strategy to achieve class-conditional distribution balancing, which automatically highlights minority groups and classes, effectively dismantling spurious correlations and producing a debiased data distribution for classification. Extensive experiments and analysis demonstrate that our approach consistently delivers state-of-the-art performance, rivaling methods that rely on bias supervision.
Authors: Chengguang Gan, Sunbowen Lee, Zhixi Cai, Yanbin Wei, Lei Zheng, Yunhao Liang, Shiwen Ni, Tatsunori Mori
Abstract: Mutual Reinforcement Effect (MRE) is an emerging subfield at the intersection of information extraction and model interpretability. MRE aims to leverage the mutual understanding between tasks of different granularities, enhancing the performance of both coarse-grained and fine-grained tasks through joint modeling. While MRE has been explored and validated in the textual domain, its applicability to visual and multimodal domains remains unexplored. In this work, we extend MRE to the multimodal information extraction domain for the first time. Specifically, we introduce a new task: Multimodal Mutual Reinforcement Effect (M-MRE), and construct a corresponding dataset to support this task. To address the challenges posed by M-MRE, we further propose a Prompt Format Adapter (PFA) that is fully compatible with various Large Vision-Language Models (LVLMs). Experimental results demonstrate that MRE can also be observed in the M-MRE task, a multimodal text-image understanding scenario. This provides strong evidence that MRE facilitates mutual gains across three interrelated tasks, confirming its generalizability beyond the textual domain.
Authors: Hassan Keshvarikhojasteh, Mihail Tifrea, Sibylle Hess, Josien P. W. Pluim, Mitko Veta
Abstract: Multiple instance learning (MIL) is a promising approach for weakly supervised classification in pathology using whole slide images (WSIs). However, conventional MIL methods such as Attention-Based Deep Multiple Instance Learning (ABMIL) typically disregard spatial interactions among patches that are crucial to pathological diagnosis. Recent advancements, such as Transformer based MIL (TransMIL), have incorporated spatial context and inter-patch relationships. However, it remains unclear whether explicitly modeling patch relationships yields similar performance gains in ABMIL, which relies solely on Multi-Layer Perceptrons (MLPs). In contrast, TransMIL employs Transformer-based layers, introducing a fundamental architectural shift at the cost of substantially increased computational complexity. In this work, we enhance the ABMIL framework by integrating interaction-aware representations to address this question. Our proposed model, Global ABMIL (GABMIL), explicitly captures inter-instance dependencies while preserving computational efficiency. Experimental results on two publicly available datasets for tumor subtyping in breast and lung cancers demonstrate that GABMIL achieves up to a 7 percentage point improvement in AUPRC and a 5 percentage point increase in the Kappa score over ABMIL, with minimal or no additional computational overhead. These findings underscore the importance of incorporating patch interactions within MIL frameworks.
Authors: Nikita Gabdullin
Abstract: Hessians of neural network (NN) contain essential information about the curvature of NN loss landscapes which can be used to estimate NN generalization capabilities. We have previously proposed generalization criteria that rely on the observation that Hessian eigenvalue spectral density (HESD) behaves similarly for a wide class of NNs. This paper further studies their applicability by investigating factors that can result in different types of HESD. We conduct a wide range of experiments showing that HESD mainly has positive eigenvalues (MP-HESD) for NN training and fine-tuning with various optimizers on different datasets with different preprocessing and augmentation procedures. We also show that mainly negative HESD (MN-HESD) is a consequence of external gradient manipulation, indicating that the previously proposed Hessian analysis methodology cannot be applied in such cases. We also propose criteria and corresponding conditions to determine HESD type and estimate NN generalization potential. These HESD types and previously proposed generalization criteria are combined into a unified HESD analysis methodology. Finally, we discuss how HESD changes during training, and show the occurrence of quasi-singular (QS) HESD and its influence on the proposed methodology and on the conventional assumptions about the relation between Hessian eigenvalues and NN loss landscape curvature.
Authors: Abderrachid Hamrani, Daniela Leizaola, Renato Sousa, Jose P. Ponce, Stanley Mathis, David G. Armstrong, Anuradha Godavarty
Abstract: Diabetic foot ulcers (DFUs) pose a significant challenge in healthcare, requiring precise and efficient wound assessment to enhance patient outcomes. This study introduces the Attention Diffusion Zero-shot Unsupervised System (ADZUS), a novel text-guided diffusion model that performs wound segmentation without relying on labeled training data. Unlike conventional deep learning models, which require extensive annotation, ADZUS leverages zero-shot learning to dynamically adapt segmentation based on descriptive prompts, offering enhanced flexibility and adaptability in clinical applications. Experimental evaluations demonstrate that ADZUS surpasses traditional and state-of-the-art segmentation models, achieving an IoU of 86.68\% and the highest precision of 94.69\% on the chronic wound dataset, outperforming supervised approaches such as FUSegNet. Further validation on a custom-curated DFU dataset reinforces its robustness, with ADZUS achieving a median DSC of 75\%, significantly surpassing FUSegNet's 45\%. The model's text-guided segmentation capability enables real-time customization of segmentation outputs, allowing targeted analysis of wound characteristics based on clinical descriptions. Despite its competitive performance, the computational cost of diffusion-based inference and the need for potential fine-tuning remain areas for future improvement. ADZUS represents a transformative step in wound segmentation, providing a scalable, efficient, and adaptable AI-driven solution for medical imaging.
Authors: Farhad Pourkamali-Anaraki
Abstract: This paper presents a comprehensive empirical analysis of conformal prediction methods on a challenging aerial image dataset featuring diverse events in unconstrained environments. Conformal prediction is a powerful post-hoc technique that takes the output of any classifier and transforms it into a set of likely labels, providing a statistical guarantee on the coverage of the true label. Unlike evaluations on standard benchmarks, our study addresses the complexities of data-scarce and highly variable real-world settings. We investigate the effectiveness of leveraging pretrained models (MobileNet, DenseNet, and ResNet), fine-tuned with limited labeled data, to generate informative prediction sets. To further evaluate the impact of calibration, we consider two parallel pipelines (with and without temperature scaling) and assess performance using two key metrics: empirical coverage and average prediction set size. This setup allows us to systematically examine how calibration choices influence the trade-off between reliability and efficiency. Our findings demonstrate that even with relatively small labeled samples and simple nonconformity scores, conformal prediction can yield valuable uncertainty estimates for complex tasks. Moreover, our analysis reveals that while temperature scaling is often employed for calibration, it does not consistently lead to smaller prediction sets, underscoring the importance of careful consideration in its application. Furthermore, our results highlight the significant potential of model compression techniques within the conformal prediction pipeline for deployment in resource-constrained environments. Based on our observations, we advocate for future research to delve into the impact of noisy or ambiguous labels on conformal prediction performance and to explore effective model reduction strategies.
Authors: Asier Bikandi, Muhammad Shaheer, Hriday Bavle, Jayan Jevanesan, Holger Voos, Jose Luis Sanchez-Lopez
Abstract: Augmented reality (AR) applications for construction monitoring rely on real-time environmental tracking to visualize architectural elements. However, construction sites present significant challenges for traditional tracking methods due to featureless surfaces, dynamic changes, and drift accumulation, leading to misalignment between digital models and the physical world. This paper proposes a BIM-aware drift correction method to address these challenges. Instead of relying solely on SLAM-based localization, we align ``as-built" detected planes from the real-world environment with ``as-planned" architectural planes in BIM. Our method performs robust plane matching and computes a transformation (TF) between SLAM (S) and BIM (B) origin frames using optimization techniques, minimizing drift over time. By incorporating BIM as prior structural knowledge, we can achieve improved long-term localization and enhanced AR visualization accuracy in noisy construction environments. The method is evaluated through real-world experiments, showing significant reductions in drift-induced errors and optimized alignment consistency. On average, our system achieves a reduction of 52.24% in angular deviations and a reduction of 60.8% in the distance error of the matched walls compared to the initial manual alignment by the user.
Authors: Yoeri Poels, Alessandro Pau, Christian Donner, Giulio Romanelli, Olivier Sauter, Cristina Venturini, Vlado Menkovski, the TCV team, the WPTE team
Abstract: When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for future devices. Unfortunately, disruptions are not fully understood, with many different underlying causes that are difficult to anticipate. Data-driven models have shown success in predicting them, but they only provide limited interpretability. On the other hand, large-scale statistical analyses have been a great asset to understanding disruptive patterns. In this paper, we leverage data-driven methods to find an interpretable representation of the plasma state for disruption characterization. Specifically, we use a latent variable model to represent diagnostic measurements as a low-dimensional, latent representation. We build upon the Variational Autoencoder (VAE) framework, and extend it for (1) continuous projections of plasma trajectories; (2) a multimodal structure to separate operating regimes; and (3) separation with respect to disruptive regimes. Subsequently, we can identify continuous indicators for the disruption rate and the disruptivity based on statistical properties of measurement data. The proposed method is demonstrated using a dataset of approximately 1600 TCV discharges, selecting for flat-top disruptions or regular terminations. We evaluate the method with respect to (1) the identified disruption risk and its correlation with other plasma properties; (2) the ability to distinguish different types of disruptions; and (3) downstream analyses. For the latter, we conduct a demonstrative study on identifying parameters connected to disruptions using counterfactual-like analysis. Overall, the method can adequately identify distinct operating regimes characterized by varying proximity to disruptions in an interpretable manner.
Authors: Shucheng Gong, Lingzhe Zhao, Wenpu Li, Hong Xie, Yin Zhang, Shiyu Zhao, Peidong Liu
Abstract: Recently, photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), have garnered widespread attention due to their superior performance. However, most works rely on low dynamic range (LDR) images, which limits the capturing of richer scene details. Some prior works have focused on high dynamic range (HDR) scene reconstruction, typically require capturing of multi-view sharp images with different exposure times at fixed camera positions during exposure times, which is time-consuming and challenging in practice. For a more flexible data acquisition, we propose a one-stage method: \textbf{CasualHDRSplat} to easily and robustly reconstruct the 3D HDR scene from casually captured videos with auto-exposure enabled, even in the presence of severe motion blur and varying unknown exposure time. \textbf{CasualHDRSplat} contains a unified differentiable physical imaging model which first applies continuous-time trajectory constraint to imaging process so that we can jointly optimize exposure time, camera response function (CRF), camera poses, and sharp 3D HDR scene. Extensive experiments demonstrate that our approach outperforms existing methods in terms of robustness and rendering quality. Our source code will be available at https://github.com/WU-CVGL/CasualHDRSplat
Authors: Wenzhao Li, Tianhao Wu, Fangcheng Zhong, Cengiz Oztireli
Abstract: The radiance fields style transfer is an emerging field that has recently gained popularity as a means of 3D scene stylization, thanks to the outstanding performance of neural radiance fields in 3D reconstruction and view synthesis. We highlight a research gap in radiance fields style transfer, the lack of sufficient perceptual controllability, motivated by the existing concept in the 2D image style transfer. In this paper, we present ARF-Plus, a 3D neural style transfer framework offering manageable control over perceptual factors, to systematically explore the perceptual controllability in 3D scene stylization. Four distinct types of controls - color preservation control, (style pattern) scale control, spatial (selective stylization area) control, and depth enhancement control - are proposed and integrated into this framework. Results from real-world datasets, both quantitative and qualitative, show that the four types of controls in our ARF-Plus framework successfully accomplish their corresponding perceptual controls when stylizing 3D scenes. These techniques work well for individual style inputs as well as for the simultaneous application of multiple styles within a scene. This unlocks a realm of limitless possibilities, allowing customized modifications of stylization effects and flexible merging of the strengths of different styles, ultimately enabling the creation of novel and eye-catching stylistic effects on 3D scenes.
Authors: Ziyun Wang, Friedhelm Hamann, Kenneth Chaney, Wen Jiang, Guillermo Gallego, Kostas Daniilidis
Abstract: We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream. Conventional cameras struggle with high-speed motion capture due to bandwidth and dynamic range limitations. Event cameras are ideal sensors to solve this problem because they encode compressed change information at high temporal resolution. In this work, we tackle the problem of event-based continuous color video decompression, pairing single static color frames and event data to reconstruct temporally continuous videos. Our approach combines continuous long-range motion modeling with a neural synthesis model, enabling frame prediction at arbitrary times within the events. Our method only requires an initial image, thus increasing the robustness to sudden motions, light changes, minimizing the prediction latency, and decreasing bandwidth usage. We also introduce a novel single-lens beamsplitter setup that acquires aligned images and events, and a novel and challenging Event Extreme Decompression Dataset (E2D2) that tests the method in various lighting and motion profiles. We thoroughly evaluate our method by benchmarking color frame reconstruction, outperforming the baseline methods by 3.61 dB in PSNR and by 33% decrease in LPIPS, as well as showing superior results on two downstream tasks.
Authors: Huiyuan Yu, Jia He, Maggie Cheng
Abstract: Orthogonal Matching Pursuit (OMP) has been a powerful method in sparse signal recovery and approximation. However OMP suffers computational issue when the signal has large number of non-zeros. This paper advances OMP in two fronts: it offers a fast algorithm for the orthogonal projection of the input signal at each iteration, and a new selection criterion for making the greedy choice, which reduces the number of iterations it takes to recover the signal. The proposed modifications to OMP directly reduce the computational complexity. Experiment results show significant improvement over the classical OMP in computation time. The paper also provided a sufficient condition for exact recovery under the new greedy choice criterion. For general signals that may not have sparse representations, the paper provides a bound for the approximation error. The approximation error is at the same order as OMP but is obtained within fewer iterations and less time.
Authors: Ziyue Zhang, Mingbao Lin, Quanjian Song, Yuxin Zhang, Rongrong Ji
Abstract: We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing everything in one prompt can be difficult, and second, users often need to add objects into the generated image. To accommodate with real world, our ObjectAdd maintains accurate image consistency after adding objects with technical innovations in: (1) embedding-level concatenation to ensure correct text embedding coalesce; (2) object-driven layout control with latent and attention injection to ensure objects accessing user-specified area; (3) prompted image inpainting in an attention refocusing & object expansion fashion to ensure rest of the image stays the same. With a text-prompted image, our ObjectAdd allows users to specify a box and an object, and achieves: (1) adding object inside the box area; (2) exact content outside the box area; (3) flawless fusion between the two areas
Authors: Fakrul Islam Tushar, Avivah Wang, Lavsen Dahal, Michael R. Harowicz, Kyle J. Lafata, Tina D. Tailor, Joseph Y. Lo
Abstract: Lung cancer remains the leading cause of cancer-related mortality worldwide, and early detection through low-dose computed tomography (LDCT) has shown significant promise in reducing death rates. With the growing integration of artificial intelligence (AI) into medical imaging, the development and evaluation of robust AI models require access to large, well-annotated datasets. In this study, we introduce the utility of Duke Lung Cancer Screening (DLCS) Dataset, the largest open-access LDCT dataset with over 2,000 scans and 3,000 expert-verified nodules. We benchmark deep learning models for both 3D nodule detection and lung cancer classification across internal and external datasets including LUNA16, LUNA25, and NLST-3D+. For detection, we develop two MONAI-based RetinaNet models (DLCSDmD and LUNA16-mD), evaluated using the Competition Performance Metric (CPM). For classification, we compare five models, including state-of-the-art pretrained models (Models Genesis, Med3D), a selfsupervised foundation model (FMCB), a randomly initialized ResNet50, and proposed a novel Strategic Warm-Start++ (SWS++) model. SWS++ uses curated candidate patches to pretrain a classification backbone within the same detection pipeline, enabling task-relevant feature learning. Our models demonstrated strong generalizability, with SWS++ achieving comparable or superior performance to existing foundational models across multiple datasets (AUC: 0.71 to 0.90). All code, models, and data are publicly released to promote reproducibility and collaboration. This work establishes a standardized benchmarking resource for lung cancer AI research, supporting future efforts in model development, validation, and clinical translation.
Authors: Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Ahmet Enis Cetin, Ulas Bagci
Abstract: Central to the Transformer architectures' effectiveness is the self-attention mechanism, a function that maps queries, keys, and values into a high-dimensional vector space. However, training the attention weights of queries, keys, and values is non-trivial from a state of random initialization. In this paper, we propose two methods. (i) We first address the initialization problem of Vision Transformers by introducing a simple, yet highly innovative, initialization approach utilizing discrete cosine transform (DCT) coefficients. Our proposed DCT-based \textit{attention} initialization marks a significant gain compared to traditional initialization strategies; offering a robust foundation for the attention mechanism. Our experiments reveal that the DCT-based initialization enhances the accuracy of Vision Transformers in classification tasks. (ii) We also recognize that since DCT effectively decorrelates image information in the frequency domain, this decorrelation is useful for compression because it allows the quantization step to discard many of the higher-frequency components. Based on this observation, we propose a novel DCT-based compression technique for the attention function of Vision Transformers. Since high-frequency DCT coefficients usually correspond to noise, we truncate the high-frequency DCT components of the input patches. Our DCT-based compression reduces the size of weight matrices for queries, keys, and values. While maintaining the same level of accuracy, our DCT compressed Swin Transformers obtain a considerable decrease in the computational overhead.
Authors: Jingcheng Li, Ye Qiao, Haocheng Xu, Sitao Huang
Abstract: Images captured under low-light scenarios often suffer from low quality. Previous CNN-based deep learning methods often involve using Retinex theory. Nevertheless, most of them cannot perform well in more complicated datasets like LOL-v2 while consuming too much computational resources. Besides, some of these methods require sophisticated training at different stages, making the procedure even more time-consuming and tedious. In this paper, we propose a more accurate, concise, and one-stage Retinex theory based framework, RSEND. RSEND first divides the low-light image into the illumination map and reflectance map, then captures the important details in the illumination map and performs light enhancement. After this step, it refines the enhanced gray-scale image and does element-wise matrix multiplication with the reflectance map. By denoising the output it has from the previous step, it obtains the final result. In all the steps, RSEND utilizes Squeeze and Excitation network to better capture the details. Comprehensive quantitative and qualitative experiments show that our Efficient Retinex model significantly outperforms other CNN-based models, achieving a PSNR improvement ranging from 0.44 dB to 4.2 dB in different datasets and even outperforms transformer-based models in the LOL-v2-real dataset.
Authors: Corn\'e Verburg, Alexander Heinlein, Eric C. Cyr
Abstract: The segmentation of ultra-high resolution images poses challenges such as loss of spatial information or computational inefficiency. In this work, a novel approach that combines encoder-decoder architectures with domain decomposition strategies to address these challenges is proposed. Specifically, a domain decomposition-based U-Net (DDU-Net) architecture is introduced, which partitions input images into non-overlapping patches that can be processed independently on separate devices. A communication network is added to facilitate inter-patch information exchange to enhance the understanding of spatial context. Experimental validation is performed on a synthetic dataset that is designed to measure the effectiveness of the communication network. Then, the performance is tested on the DeepGlobe land cover classification dataset as a real-world benchmark data set. The results demonstrate that the approach, which includes inter-patch communication for images divided into $16\times16$ non-overlapping subimages, achieves a $2-3\,\%$ higher intersection over union (IoU) score compared to the same network without inter-patch communication. The performance of the network which includes communication is equivalent to that of a baseline U-Net trained on the full image, showing that our model provides an effective solution for segmenting ultra-high-resolution images while preserving spatial context. The code is available at https://github.com/corne00/DDU-Net.
Authors: Dongyang Liu, Shitian Zhao, Le Zhuo, Weifeng Lin, Yi Xin, Xinyue Li, Qi Qin, Yu Qiao, Hongsheng Li, Peng Gao
Abstract: We present Lumina-mGPT, a family of multimodal autoregressive models capable of various vision and language tasks, particularly excelling in generating flexible photorealistic images from text descriptions. By initializing from multimodal Generative PreTraining (mGPT), we demonstrate that decoder-only Autoregressive (AR) model can achieve image generation performance comparable to modern diffusion models with high efficiency through Flexible Progressive Supervised Fine-tuning (FP-SFT). Equipped with our proposed Unambiguous image Representation (UniRep), Lumina-mGPT can flexibly generate high-quality images of varying aspect ratios. Building on the strong image generation capabilities, we further explore Ominiponent Supervised Fine-tuning (Omni-SFT), an initial attempt to elevate Lumina-mGPT into a unified multi-modal generalist. The resulting model demonstrates versatile multimodal capabilities, including visual generation tasks like text-to-image/multiview generation and controllable generation, visual recognition tasks like segmentation and depth estimation, and vision-language tasks like multi-turn visual question answering, showing the rosy potential of the technical direction. Codes and checkpoints are available at https://github.com/Alpha-VLLM/Lumina-mGPT.
Authors: Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
Abstract: Sequential multiple-instance learning involves learning representations of sets distributed across discrete timesteps. In many real-world applications, modeling both the internal structure of sets and their temporal relationships across time is essential for capturing complex underlying patterns. However, existing methods either focus on learning set representations at a static level, ignoring temporal dynamics, or treat sequences as ordered lists of individual elements, lacking explicit mechanisms to represent sets. In this work, we propose Set2Seq Transformer, a novel architecture that jointly models permutation-invariant set structure and temporal dependencies by learning temporal and positional-aware representations of sets within a sequence in an end-to-end multimodal manner. We evaluate our Set2Seq Transformer on two tasks that require modeling both set structure alongside temporal and positional patterns, but differ significantly in domain, modality, and objective. First, we consider a fine-art analysis task, modeling artists' oeuvres for predicting artistic success using a novel dataset, WikiArt-Seq2Rank. Second, we utilize our Set2Seq Transformer for a short-term wildfire danger forecasting task. Through extensive experimentation, we show that our Set2Seq Transformer significantly improves over traditional static multiple-instance learning methods by effectively learning permutation-invariant set, temporal, and positional-aware representations across diverse domains, modalities, and tasks. We will release both the dataset and model implementations on GitHub.
Authors: Senkang Hu, Zhengru Fang, Zihan Fang, Yiqin Deng, Xianhao Chen, Yuguang Fang, Sam Kwong
Abstract: Ramp merging is one of the bottlenecks in traffic systems, which commonly cause traffic congestion, accidents, and severe carbon emissions. In order to address this essential issue and enhance the safety and efficiency of connected and autonomous vehicles (CAVs) at multi-lane merging zones, we propose a novel collaborative decision-making framework, named AgentsCoMerge, to leverage large language models (LLMs). Specifically, we first design a scene observation and understanding module to allow an agent to capture the traffic environment. Then we propose a hierarchical planning module to enable the agent to make decisions and plan trajectories based on the observation and the agent's own state. In addition, in order to facilitate collaboration among multiple agents, we introduce a communication module to enable the surrounding agents to exchange necessary information and coordinate their actions. Finally, we develop a reinforcement reflection guided training paradigm to further enhance the decision-making capability of the framework. Extensive experiments are conducted to evaluate the performance of our proposed method, demonstrating its superior efficiency and effectiveness for multi-agent collaborative decision-making under various ramp merging scenarios.
Authors: Dewen Zeng, Yawen Wu, Xinrong Hu, Xiaowei Xu, Yiyu Shi
Abstract: Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its efficacy is constrained as the nearest neighbor algorithm primarily identifies "easy" positive pairs, where the representations are already closely located in the embedding space. In this paper, we introduce a novel approach called Contrastive Learning with Synthetic Positives (CLSP) that utilizes synthetic images, generated by an unconditional diffusion model, as the additional positives to help the model learn from diverse positives. Through feature interpolation in the diffusion model sampling process, we generate images with distinct backgrounds yet similar semantic content to the anchor image. These images are considered "hard" positives for the anchor image, and when included as supplementary positives in the contrastive loss, they contribute to a performance improvement of over 2% and 1% in linear evaluation compared to the previous NNCLR and All4One methods across multiple benchmark datasets such as CIFAR10, achieving state-of-the-art methods. On transfer learning benchmarks, CLSP outperforms existing SSL frameworks on 6 out of 8 downstream datasets. We believe CLSP establishes a valuable baseline for future SSL studies incorporating synthetic data in the training process.
Authors: Yi-Chia Chang, Adam J. Stewart, Favyen Bastani, Piper Wolters, Shreya Kannan, George R. Huber, Jingtong Wang, Arindam Banerjee
Abstract: Foundation models pre-trained using self-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. The Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed nations not transferring well to data-scarce developing nations -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select five crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, while only 100 labeled images are sufficient for achieving high overall accuracy, 900 images are required to achieve high average accuracy due to class imbalance. All harmonized datasets and experimental code are open-source and available for download.
Authors: Chen Liu, Danqi Liao, Alejandro Parada-Mayorga, Alejandro Ribeiro, Marcello DiStasio, Smita Krishnaswamy
Abstract: The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for biomedical research and clinical diagnostics. However, accurately annotating densely packed information in these images remains a major challenge. To address this, we introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks. DiffKillR employs two complementary neural networks: one that learns a diffeomorphism-invariant feature space for robust cell matching and another that computes the precise warping field between cells for annotation mapping. Using a small set of annotated archetypes, DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling. More importantly, it is suitable for any type of pixel-level annotation. We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods. The code is available at https://github.com/KrishnaswamyLab/DiffKillR.
Authors: Zhuoman Liu, Weicai Ye, Yan Luximon, Pengfei Wan, Di Zhang
Abstract: Realistic simulation of dynamic scenes requires accurately capturing diverse material properties and modeling complex object interactions grounded in physical principles. However, existing methods are constrained to basic material types with limited predictable parameters, making them insufficient to represent the complexity of real-world materials. We introduce PhysFlow, a novel approach that leverages multi-modal foundation models and video diffusion to achieve enhanced 4D dynamic scene simulation. Our method utilizes multi-modal models to identify material types and initialize material parameters through image queries, while simultaneously inferring 3D Gaussian splats for detailed scene representation. We further refine these material parameters using video diffusion with a differentiable Material Point Method (MPM) and optical flow guidance rather than render loss or Score Distillation Sampling (SDS) loss. This integrated framework enables accurate prediction and realistic simulation of dynamic interactions in real-world scenarios, advancing both accuracy and flexibility in physics-based simulations.
Authors: S. P. Sharan, Minkyu Choi, Sahil Shah, Harsh Goel, Mohammad Omama, Sandeep Chinchali
Abstract: Recent advancements in text-to-video models such as Sora, Gen-3, MovieGen, and CogVideoX are pushing the boundaries of synthetic video generation, with adoption seen in fields like robotics, autonomous driving, and entertainment. As these models become prevalent, various metrics and benchmarks have emerged to evaluate the quality of the generated videos. However, these metrics emphasize visual quality and smoothness, neglecting temporal fidelity and text-to-video alignment, which are crucial for safety-critical applications. To address this gap, we introduce NeuS-V, a novel synthetic video evaluation metric that rigorously assesses text-to-video alignment using neuro-symbolic formal verification techniques. Our approach first converts the prompt into a formally defined Temporal Logic (TL) specification and translates the generated video into an automaton representation. Then, it evaluates the text-to-video alignment by formally checking the video automaton against the TL specification. Furthermore, we present a dataset of temporally extended prompts to evaluate state-of-the-art video generation models against our benchmark. We find that NeuS-V demonstrates a higher correlation by over 5x with human evaluations when compared to existing metrics. Our evaluation further reveals that current video generation models perform poorly on these temporally complex prompts, highlighting the need for future work in improving text-to-video generation capabilities.
Authors: Zhenyu Yu, Jinnian Wang, Mohd Yamani Idna Idris
Abstract: The forest serves as the most significant terrestrial carbon stock mechanism, effectively reducing atmospheric CO2 concentrations and mitigating climate change. Remote sensing provides high data accuracy and enables large-scale observations. Optical images facilitate long-term monitoring, which is crucial for future carbon stock estimation studies. This study focuses on Huize County, Qujing City, Yunnan Province, China, utilizing GF-1 WFV satellite imagery. The KD-VGG and KD-UNet modules were introduced for initial feature extraction, and the improved implicit diffusion model (IIDM) was proposed. The results showed: (1) The VGG module improved initial feature extraction, improving accuracy, and reducing inference time with optimized model parameters. (2) The Cross-attention + MLPs module enabled effective feature fusion, establishing critical relationships between global and local features, achieving high-accuracy estimation. (3) The IIDM model, a novel contribution, demonstrated the highest estimation accuracy with an RMSE of 12.17%, significantly improving by 41.69% to 42.33% compared to the regression model. In carbon stock estimation, the generative model excelled in extracting deeper features, significantly outperforming other models, demonstrating the feasibility of AI-generated content in quantitative remote sensing. The 16-meter resolution estimates provide a robust basis for tailoring forest carbon sink regulations, enhancing regional carbon stock management.
Authors: Shekhar Madhav Khairnar, Huu Phong Nguyen, Alexis Desir, Carla Holcomb, Daniel J. Scott, Ganesh Sankaranarayanan
Abstract: Automated assessment of surgical skills using artificial intelligence (AI) provides trainees with instantaneous feedback. After bimanual tool motions are captured, derived kinematic metrics are reliable predictors of performance in laparoscopic tasks. Implementing automated tool tracking requires time-intensive human annotation. We developed AI-based tool tracking using the Segment Anything Model (SAM) to eliminate the need for human annotators. Here, we describe a study evaluating the usefulness of our tool tracking model in automated assessment during a laparoscopic suturing task in the fundoplication procedure. An automated tool tracking model was applied to recorded videos of Nissen fundoplication on porcine bowel. Surgeons were grouped as novices (PGY1-2) and experts (PGY3-5, attendings). The beginning and end of each suturing step were segmented, and motions of the left and right tools were extracted. A low-pass filter with a 24 Hz cut-off frequency removed noise. Performance was assessed using supervised and unsupervised models, and an ablation study compared results. Kinematic features--RMS velocity, RMS acceleration, RMS jerk, total path length, and Bimanual Dexterity--were extracted and analyzed using Logistic Regression, Random Forest, Support Vector Classifier, and XGBoost. PCA was performed for feature reduction. For unsupervised learning, a Denoising Autoencoder (DAE) model with classifiers, such as a 1-D CNN and traditional models, was trained. Data were extracted for 28 participants (9 novices, 19 experts). Supervised learning with PCA and Random Forest achieved an accuracy of 0.795 and an F1 score of 0.778. The unsupervised 1-D CNN achieved superior results with an accuracy of 0.817 and an F1 score of 0.806, eliminating the need for kinematic feature computation. We demonstrated an AI model capable of automated performance classification, independent of human annotation.
Authors: Jiajun Deng, Tianyu He, Li Jiang, Tianyu Wang, Feras Dayoub, Ian Reid
Abstract: Current 3D Large Multimodal Models (3D LMMs) have shown tremendous potential in 3D-vision-based dialogue and reasoning. However, how to further enhance 3D LMMs to achieve fine-grained scene understanding and facilitate flexible human-agent interaction remains a challenging problem. In this work, we introduce 3D-LLaVA, a simple yet highly powerful 3D LMM designed to act as an intelligent assistant in comprehending, reasoning, and interacting with the 3D world. Unlike existing top-performing methods that rely on complicated pipelines-such as offline multi-view feature extraction or additional task-specific heads-3D-LLaVA adopts a minimalist design with integrated architecture and only takes point clouds as input. At the core of 3D-LLaVA is a new Omni Superpoint Transformer (OST), which integrates three functionalities: (1) a visual feature selector that converts and selects visual tokens, (2) a visual prompt encoder that embeds interactive visual prompts into the visual token space, and (3) a referring mask decoder that produces 3D masks based on text description. This versatile OST is empowered by the hybrid pretraining to obtain perception priors and leveraged as the visual connector that bridges the 3D data to the LLM. After performing unified instruction tuning, our 3D-LLaVA reports impressive results on various benchmarks.
Authors: Josh Bruegger, Diana Ioana Catana, Vanja Macovaz, Matias Valdenegro-Toro, Matthia Sabatelli, Marco Zullich
Abstract: The attribution of the author of an art piece is typically a laborious manual process, usually relying on subjective evaluations of expert figures. However, there are some situations in which quantitative features of the artwork can support these evaluations. The extraction of these features can sometimes be automated, for instance, with the use of Machine Learning (ML) techniques. An example of these features is represented by repeated, mechanically impressed patterns, called punches, present chiefly in 13th and 14th-century panel paintings from Tuscany. Previous research in art history showcased a strong connection between the shapes of punches and specific artists or workshops, suggesting the possibility of using these quantitative cues to support the attribution. In the present work, we first collect a dataset of large-scale images of these panel paintings. Then, using YOLOv10, a recent and popular object detection model, we train a ML pipeline to perform object detection on the punches contained in the images. Due to the large size of the images, the detection procedure is split across multiple frames by adopting a sliding-window approach with overlaps, after which the predictions are combined for the whole image using a custom non-maximal suppression routine. Our results indicate how art historians working in the field can reliably use our method for the identification and extraction of punches.
Authors: Nicolas von L\"utzow, Matthias Nie{\ss}ner
Abstract: Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we explore an alternative volumetric scene representation. More specifically, we introduce two new scene representations based on linear primitives - octahedra and tetrahedra - both of which define homogeneous volumes bounded by triangular faces. To optimize these primitives, we present a differentiable rasterizer that runs efficiently on GPUs, allowing end-to-end gradient-based optimization while maintaining real-time rendering capabilities. Through experiments on real-world datasets, we demonstrate comparable performance to state-of-the-art volumetric methods while requiring fewer primitives to achieve similar reconstruction fidelity. Our findings deepen the understanding of 3D representations by providing insights into the fidelity and performance characteristics of transparent polyhedra and suggest that adopting novel primitives can expand the available design space.
Authors: Ketan Kotwal, Sebastien Marcel
Abstract: Demographic fairness in face recognition (FR) has emerged as a critical area of research, given its impact on fairness, equity, and reliability across diverse applications. As FR technologies are increasingly deployed globally, disparities in performance across demographic groups-- such as race, ethnicity, and gender-- have garnered significant attention. These biases not only compromise the credibility of FR systems but also raise ethical concerns, especially when these technologies are employed in sensitive domains. This review consolidates extensive research efforts providing a comprehensive overview of the multifaceted aspects of demographic fairness in FR. We systematically examine the primary causes, datasets, assessment metrics, and mitigation approaches associated with demographic disparities in FR. By categorizing key contributions in these areas, this work provides a structured approach to understanding and addressing the complexity of this issue. Finally, we highlight current advancements and identify emerging challenges that need further investigation. This article aims to provide researchers with a unified perspective on the state-of-the-art while emphasizing the critical need for equitable and trustworthy FR systems.
Authors: Guillaume Jeanneret, Lo\"ic Simon, Fr\'ed\'eric Jurie
Abstract: Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacles to the interpretation of transformers is the self-attention mechanism, which mixes visual information across the whole image in a complex way. In this paper, we propose Hindered Transformer (HiT), a novel interpretable by design architecture inspired by visual transformers. Our proposed architecture rethinks the design of transformers to better disentangle patch influences at the classification stage. Ultimately, HiT can be interpreted as a linear combination of patch-level information. We show that the advantages of our approach in terms of explicability come with a reasonable trade-off in performance, making it an attractive alternative for applications where interpretability is paramount.
Authors: Shehreen Azad, Vibhav Vineet, Yogesh Singh Rawat
Abstract: Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed Hierachical Querying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on 10 video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis.
Authors: Hao Ai, Kunyi Wang, Zezhou Wang, Hao Lu, Jin Tian, Yaxin Luo, Peng Xing, Jen-Yuan Huang, Huaxia Li, Gen luo
Abstract: Multimodal large language models (MLLMs) have demonstrated impressive performance in various vision-language (VL) tasks, but their expensive computations still limit the real-world application. To address this issue, recent efforts aim to compress the visual features to save the computational costs of MLLMs. However, direct visual compression methods, e.g. efficient projectors, inevitably destroy the visual semantics in MLLM, especially in difficult samples. To overcome this shortcoming, we propose a novel dynamic pyramid network (DPN) for efficient MLLMs. Specifically, DPN formulates MLLM as a hierarchical structure where visual features are gradually compressed with increasing depth. In this case, even with a high compression ratio, fine-grained visual information can still be perceived in shallow layers. To maximize the benefit of DPN, we further propose an innovative Dynamic Pooling Experts (DPE) that can dynamically choose the optimal visual compression rate according to input features. With this design, harder samples will be assigned larger computations, thus preserving the model performance. To validate our approach, we conduct extensive experiments on two popular MLLMs and ten benchmarks. Experimental results show that DPN can save up to 56% average FLOPs on LLaVA while further achieving +0.74% performance gains. Besides, the generalization ability of DPN is also validated on the existing high-resolution MLLM called LLaVA-HR. The source code will be released at https://github.com/aihao2000/DPN-LLaVA.
Authors: Ximing Wen, Mallika Mainali, Anik Sen
Abstract: Vision Language Models (VLMs) have demonstrated strong reasoning capabilities in Visual Question Answering (VQA) tasks; however, their ability to perform Theory of Mind (ToM) tasks, such as inferring human intentions, beliefs, and mental states, remains underexplored. We propose an open-ended question framework to evaluate VLMs' performance across diverse categories of ToM tasks. We curated and annotated a benchmark dataset of 30 images and evaluated the performance of four VLMs of varying sizes. Our results show that the GPT-4 model outperformed all the others, with only one smaller model, GPT-4o-mini, achieving comparable performance. We observed that VLMs often struggle to infer intentions in complex scenarios such as bullying or cheating. Our findings reveal that smaller models can sometimes infer correct intentions despite relying on incorrect visual cues. The dataset is available at https://github.com/ximingwen/ToM-AAAI25-Multimodal.
Authors: Yihao Wang, Zhong Qian, Peifeng Li
Abstract: News media, particularly video-based platforms, have become deeply embedded in daily life, concurrently amplifying risks of misinformation dissemination. Consequently, multimodal fake news detection has garnered significant research attention. However, existing datasets predominantly comprise user-generated videos characterized by crude editing and limited public engagement, whereas professionally crafted fake news videos disseminated by media outlets, often politically or virally motivated-pose substantially greater societal harm. To address this gap, we construct FMNV, a novel dataset exclusively composed of news videos published by media organizations. Through empirical analysis of existing datasets and our curated collection, we categorize fake news videos into four distinct types. Building upon this taxonomy, we employ Large Language Models (LLMs) to automatically generate deceptive content by manipulating authentic media-published news videos. Furthermore, we propose FMNVD, a baseline model featuring a dual-stream architecture integrating CLIP and Faster R-CNN for video feature extraction, enhanced by co-attention mechanisms for feature refinement and multimodal aggregation. Comparative experiments demonstrate both the generalization capability of FMNV across multiple baselines and the superior detection efficacy of FMNVD. This work establishes critical benchmarks for detecting high-impact fake news in media ecosystems while advancing methodologies for cross-modal inconsistency analysis.
Authors: Weizhi Nie, Zichun Zhang, Weijie Wang, Bruno Lepri, Anan Liu, Nicu Sebe
Abstract: Counterfactual medical image generation effectively addresses data scarcity and enhances the interpretability of medical images. However, due to the complex and diverse pathological features of medical images and the imbalanced class distribution in medical data, generating high-quality and diverse medical images from limited data is significantly challenging. Additionally, to fully leverage the information in limited data, such as anatomical structure information and generate more structurally stable medical images while avoiding distortion or inconsistency. In this paper, in order to enhance the clinical relevance of generated data and improve the interpretability of the model, we propose a novel medical image generation framework, which generates independent pathological and structural features based on causal disentanglement and utilizes text-guided modeling of pathological features to regulate the generation of counterfactual images. First, we achieve feature separation through causal disentanglement and analyze the interactions between features. Here, we introduce group supervision to ensure the independence of pathological and identity features. Second, we leverage a diffusion model guided by pathological findings to model pathological features, enabling the generation of diverse counterfactual images. Meanwhile, we enhance accuracy by leveraging a large language model to extract lesion severity and location from medical reports. Additionally, we improve the performance of the latent diffusion model on long-tailed categories through initial noise optimization.
Authors: David C Wong, Bin Wang, Gorkem Durak, Marouane Tliba, Mohamed Amine Kerkouri, Aladine Chetouani, Ahmet Enis Cetin, Cagdas Topel, Nicolo Gennaro, Camila Vendrami, Tugce Agirlar Trabzonlu, Amir Ali Rahsepar, Laetitia Perronne, Matthew Antalek, Onural Ozturk, Gokcan Okur, Andrew C. Gordon, Ayis Pyrros, Frank H Miller, Amir A Borhani, Hatice Savas, Eric M. Hart, Elizabeth A Krupinski, Ulas Bagci
Abstract: Eye-tracking analysis plays a vital role in medical imaging, providing key insights into how radiologists visually interpret and diagnose clinical cases. In this work, we first analyze radiologists' attention and agreement by measuring the distribution of various eye-movement patterns, including saccades direction, amplitude, and their joint distribution. These metrics help uncover patterns in attention allocation and diagnostic strategies. Furthermore, we investigate whether and how doctors' gaze behavior shifts when viewing authentic (Real) versus deep-learning-generated (Fake) images. To achieve this, we examine fixation bias maps, focusing on first, last, short, and longest fixations independently, along with detailed saccades patterns, to quantify differences in gaze distribution and visual saliency between authentic and synthetic images.
Authors: Vidi Team, Celong Liu, Chia-Wen Kuo, Dawei Du, Fan Chen, Guang Chen, Jiamin Yuan, Lingxi Zhang, Lu Guo, Lusha Li, Longyin Wen, Qingyu Chen, Rachel Deng, Sijie Zhu, Stuart Siew, Tong Jin, Wei Lu, Wen Zhong, Xiaohui Shen, Xin Gu, Xing Mei, Xueqiong Qu
Abstract: Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support the creation of high-quality large-scale video content, a modern pipeline requires a comprehensive understanding of both the raw input materials (e.g., the unedited footage captured by cameras) and the editing components (e.g., visual effects). In video editing scenarios, models must process multiple modalities (e.g., vision, audio, text) with strong background knowledge and handle flexible input lengths (e.g., hour-long raw videos), which poses significant challenges for traditional models. In this report, we introduce Vidi, a family of Large Multimodal Models (LMMs) for a wide range of video understand editing scenarios. The first release focuses on temporal retrieval, i.e., identifying the time ranges within the input videos corresponding to a given text query, which plays a critical role in intelligent editing. The model is capable of processing hour-long videos with strong temporal understanding capability, e.g., retrieve time ranges for certain queries. To support a comprehensive evaluation in real-world scenarios, we also present the VUE-TR benchmark, which introduces five key advancements. 1) Video duration: significantly longer than videos of existing temporal retrival datasets, 2) Audio support: includes audio-based queries, 3) Query format: diverse query lengths/formats, 4) Annotation quality: ground-truth time ranges are manually annotated. 5) Evaluation metric: a refined IoU metric to support evaluation over multiple time ranges. Remarkably, Vidi significantly outperforms leading proprietary models, e.g., GPT-4o and Gemini, on the temporal retrieval task, indicating its superiority in video editing scenarios.
Authors: Saban Ozturk, Melih B. Yilmaz, Muti Kara, M. Talat Yavuz, Aykut Ko\c{c}, Tolga \c{C}ukur
Abstract: Diagnostic imaging relies on interpreting both images and radiology reports, but the growing data volumes place significant pressure on medical experts, yielding increased errors and workflow backlogs. Medical vision-language models (med-VLMs) have emerged as a powerful framework to efficiently process multimodal imaging data, particularly in chest X-ray (CXR) evaluations, albeit their performance hinges on how well image and text representations are aligned. Existing alignment methods, predominantly based on contrastive learning, prioritize separation between disease classes over segregation of fine-grained pathology attributes like location, size or severity, leading to suboptimal representations. Here, we propose MedTrim (Meta-entity-driven Triplet mining), a novel method that enhances image-text alignment through multimodal triplet learning synergistically guided by disease class as well as adjectival and directional pathology descriptors. Unlike common alignment methods that separate broad disease classes, MedTrim leverages structured meta-entity information to preserve subtle but clinically significant intra-class variations. For this purpose, we first introduce an ontology-based entity recognition module that extracts pathology-specific meta-entities from CXR reports, as annotations on pathology attributes are rare in public datasets. For refined sample selection in triplet mining, we then introduce a novel score function that captures an aggregate measure of inter-sample similarity based on disease classes and adjectival/directional descriptors. Lastly, we introduce a multimodal triplet alignment objective for explicit within- and cross-modal alignment between samples sharing detailed pathology characteristics. Our demonstrations indicate that MedTrim improves performance in downstream retrieval and classification tasks compared to state-of-the-art alignment methods.
Authors: Duy-Tho Le, Trung Pham, Jianfei Cai, Hamid Rezatofighi
Abstract: Optimizing the similarity between parametric shapes is crucial for numerous computer vision tasks, where Intersection over Union (IoU) stands as the canonical measure. However, existing optimization methods exhibit significant shortcomings: regression-based losses like L1/L2 lack correlation with IoU, IoU-based losses are unstable and limited to simple shapes, and task-specific methods are computationally intensive and not generalizable accross domains. As a result, the current landscape of parametric shape objective functions has become scattered, with each domain proposing distinct IoU approximations. To address this, we unify the parametric shape optimization objective functions by introducing Marginalized Generalized IoU (MGIoU), a novel loss function that overcomes these challenges by projecting structured convex shapes onto their unique shape Normals to compute one-dimensional normalized GIoU. MGIoU offers a simple, efficient, fully differentiable approximation strongly correlated with IoU. We then extend MGIoU to MGIoU+ that supports optimizing unstructured convex shapes. Together, MGIoU and MGIoU+ unify parametric shape optimization across diverse applications. Experiments on standard benchmarks demonstrate that MGIoU and MGIoU+ consistently outperform existing losses while reducing loss computation latency by 10-40x. Additionally, MGIoU and MGIoU+ satisfy metric properties and scale-invariance, ensuring robustness as an objective function. We further propose MGIoU- for minimizing overlaps in tasks like collision-free trajectory prediction. Code is available at https://ldtho.github.io/MGIoU
Authors: Zhiyuan Fan, Yumeng Wang, Sandeep Polisetty, Yi R. Fung
Abstract: Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V$^2$R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment. Through extensive evaluation on 21 LVLMs, we reveal a surprising vulnerability to visual variations, in which even advanced models that excel at complex vision-language tasks significantly underperform on simple tasks such as object recognition. Interestingly, these models exhibit a distinct visual position bias that contradicts theories of effective receptive fields, and demonstrate a human-like visual acuity threshold. To identify the source of these vulnerabilities, we present a systematic framework for component-level analysis, featuring a novel visualization approach for aligned visual features. Results show that these vulnerabilities stem from error accumulation in the pipeline architecture and inadequate multimodal alignment. Complementary experiments with synthetic data further demonstrate that these limitations are fundamentally architectural deficiencies, scoring the need for architectural innovations in future LVLM designs.
Authors: Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter
Abstract: We present GameNGen, the first game engine powered entirely by a neural model that also enables real-time interaction with a complex environment over long trajectories at high quality. When trained on the classic game DOOM, GameNGen extracts gameplay and uses it to generate a playable environment that can interactively simulate new trajectories. GameNGen runs at 20 frames per second on a single TPU and remains stable over extended multi-minute play sessions. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters are only slightly better than random chance at distinguishing short clips of the game from clips of the simulation, even after 5 minutes of auto-regressive generation. GameNGen is trained in two phases: (1) an RL-agent learns to play the game and the training sessions are recorded, and (2) a diffusion model is trained to produce the next frame, conditioned on the sequence of past frames and actions. Conditioning augmentations help ensure stable auto-regressive generation over long trajectories, and decoder fine-tuning improves the fidelity of visual details and text.
Authors: Xiaotong Zhang, Alexander Broersen, Gonnie CM van Erp, Silvia L. Pintea, Jouke Dijkstra
Abstract: Improving connectivity and completeness are the most challenging aspects of liver vessel segmentation, especially for small vessels. These challenges require both learning the continuous vessel geometry and focusing on small vessel detection. However, current methods do not explicitly address these two aspects and cannot generalize well when constrained by inconsistent annotations. Here, we take advantage of the generalization of the diffusion model and explicitly integrate connectivity and completeness in our diffusion-based segmentation model. Specifically, we use a graph-attention module that adds knowledge about vessel geometry. Additionally, we perform the graph-attention at multiple-scales, thus focusing on small liver vessels. Our method outperforms five state-of-the-art medical segmentation methods on two public datasets: 3D-ircadb-01 and LiVS.
Authors: Andreas Koukounas, Georgios Mastrapas, Sedigheh Eslami, Bo Wang, Mohammad Kalim Akram, Michael G\"unther, Isabelle Mohr, Saba Sturua, Nan Wang, Han Xiao
Abstract: Contrastive Language-Image Pretraining (CLIP) has been widely used for crossmodal information retrieval and multimodal understanding tasks. However, CLIP models are mainly optimized for crossmodal vision-language tasks and underperform in single-mode text tasks. Moreover, these models are often trained on English datasets and therefore lack multilingual understanding. Additionally, from a visual understanding perspective, previous CLIP-based models exhibit insufficient understanding of visually rich documents. In this work, we propose jina-clip-v2, a contrastive vision-language model trained on text pairs, triplets and image-text pairs via a multi-task and multi-stage contrastive learning paradigm in order to support both text-only and crossmodal tasks. We employ a multilingual text encoder and expand the training dataset to include multilingual texts from 29 non-English languages, including Hindi, Chinese, German, French, and others, as well as images of visually rich documents. We evaluate the model's performance and show that jina-clip-v2 achieves notable improvements over state-of-the-art CLIP-based models in zero-shot text-only retrieval, semantic textual similarity, and crossmodal retrieval tasks in both English and multilingual settings. jina-clip-v2 also provides for flexibility in embedding dimensionality, enabling users to select the granularity of the representations. jina-clip-v2 is publicly available at https://huggingface.co/jinaai/jina-clip-v2.
Authors: Xinyang Tong, Pengxiang Ding, Yiguo Fan, Donglin Wang, Wenjie Zhang, Can Cui, Mingyang Sun, Han Zhao, Hongyin Zhang, Yonghao Dang, Siteng Huang, Shangke Lyu
Abstract: This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tuning phase, making them unsuitable for this purpose. We introduce a novel latency-free quadruped MLLM model, dubbed QUART-Online, designed to enhance inference efficiency without degrading the performance of the language foundation model. By incorporating Action Chunk Discretization (ACD), we compress the original action representation space, mapping continuous action values onto a smaller set of discrete representative vectors while preserving critical information. Subsequently, we fine-tune the MLLM to integrate vision, language, and compressed actions into a unified semantic space. Experimental results demonstrate that QUART-Online operates in tandem with the existing MLLM system, achieving real-time inference in sync with the underlying controller frequency, significantly boosting the success rate across various tasks by 65%. Our project page is https://quart-online.github.io.
Authors: Lichen Bai, Masashi Sugiyama, Zeke Xie
Abstract: The goal of diffusion generative models is to align the learned distribution with the real data distribution through gradient score matching. However, inherent limitations in training data quality, modeling strategies, and architectural design lead to inevitable gap between generated outputs and real data. To reduce this gap, we propose Weak-to-Strong Diffusion (W2SD), a novel framework that utilizes the estimated difference between existing weak and strong models (i.e., weak-to-strong difference) to bridge the gap between an ideal model and a strong model. By employing a reflective operation that alternates between denoising and inversion with weak-to-strong difference, we theoretically understand that W2SD steers latent variables along sampling trajectories toward regions of the real data distribution. W2SD is highly flexible and broadly applicable, enabling diverse improvements through the strategic selection of weak-to-strong model pairs (e.g., DreamShaper vs. SD1.5, good experts vs. bad experts in MoE). Extensive experiments demonstrate that W2SD significantly improves human preference, aesthetic quality, and prompt adherence, achieving SOTA performance across various modalities (e.g., image, video), architectures (e.g., UNet-based, DiT-based, MoE), and benchmarks. For example, Juggernaut-XL with W2SD can improve with the HPSv2 winning rate up to 90% over the original results. Moreover, the performance gains achieved by W2SD markedly outweigh its additional computational overhead, while the cumulative improvements from different weak-to-strong difference further solidify its practical utility and deployability.
Authors: Mehmet Can Yavuz, Berrin Yanikoglu
Abstract: We present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on input reconstruction via a decoder, VSSL symmetrically couples two encoders with Gaussian outputs. A momentum-updated teacher network defines a dynamic, data-dependent prior, while the student encoder produces an approximate posterior from augmented views. The reconstruction term in the ELBO is replaced with a cross-view denoising objective, preserving the analytical tractability of Gaussian KL divergence. We further introduce cosine-based formulations of KL and log-likelihood terms to enhance semantic alignment in high-dimensional latent spaces. Experiments on CIFAR-10, CIFAR-100, and ImageNet-100 show that VSSL achieves competitive or superior performance to leading self-supervised methods, including BYOL and MoCo V3. VSSL offers a scalable, probabilistically grounded approach to learning transferable representations without generative reconstruction, bridging the gap between variational modeling and modern self-supervised techniques.
Authors: Justin Namuk Kim, Yiqiao Liu, Rajath Soans, Keith Persson, Sarah Halek, Michal Tomaszewski, Jianda Yuan, Gregory Goldmacher, Antong Chen
Abstract: Accurate segmentation of longitudinal CT scans is important for monitoring tumor progression and evaluating treatment responses. However, existing 3D segmentation models solely focus on spatial information. To address this gap, we propose OmniMamba4D, a novel segmentation model designed for 4D medical images (3D images over time). OmniMamba4D utilizes a spatio-temporal tetra-orientated Mamba block to effectively capture both spatial and temporal features. Unlike traditional 3D models, which analyze single-time points, OmniMamba4D processes 4D CT data, providing comprehensive spatio-temporal information on lesion progression. Evaluated on an internal dataset comprising of 3,252 CT scans, OmniMamba4D achieves a competitive Dice score of 0.682, comparable to state-of-the-arts (SOTA) models, while maintaining computational efficiency and better detecting disappeared lesions. This work demonstrates a new framework to leverage spatio-temporal information for longitudinal CT lesion segmentation.
Authors: Oliver Mills, Philip Conaghan, Nishant Ravikumar, Samuel Relton
Abstract: Menisci are cartilaginous tissue found within the knee that contribute to joint lubrication and weight dispersal. Damage to menisci can lead to onset and progression of knee osteoarthritis (OA), a condition that is a leading cause of disability, and for which there are few effective therapies. Accurate automated segmentation of menisci would allow for earlier detection and treatment of meniscal abnormalities, as well as shedding more light on the role the menisci play in OA pathogenesis. Focus in this area has mainly used variants of convolutional networks, but there has been no attempt to utilise recent large vision transformer segmentation models. The Segment Anything Model (SAM) is a so-called foundation segmentation model, which has been found useful across a range of different tasks due to the large volume of data used for training the model. In this study, SAM was adapted to perform fully-automated segmentation of menisci from 3D knee magnetic resonance images. A 3D U-Net was also trained as a baseline. It was found that, when fine-tuning only the decoder, SAM was unable to compete with 3D U-Net, achieving a Dice score of $0.81\pm0.03$, compared to $0.87\pm0.03$, on a held-out test set. When fine-tuning SAM end-to-end, a Dice score of $0.87\pm0.03$ was achieved. The performance of both the end-to-end trained SAM configuration and the 3D U-Net were comparable to the winning Dice score ($0.88\pm0.03$) in the IWOAI Knee MRI Segmentation Challenge 2019. Performance in terms of the Hausdorff Distance showed that both configurations of SAM were inferior to 3D U-Net in matching the meniscus morphology. Results demonstrated that, despite its generalisability, SAM was unable to outperform a basic 3D U-Net in meniscus segmentation, and may not be suitable for similar 3D medical image segmentation tasks also involving fine anatomical structures with low contrast and poorly-defined boundaries.
Authors: Sahara Sheikholeslami, Ladislau B\"ol\"oni
Abstract: Robotic manipulation requires explicit or implicit knowledge of the robot's joint positions. Precise proprioception is standard in high-quality industrial robots but is often unavailable in inexpensive robots operating in unstructured environments. In this paper, we ask: to what extent can a fast, single-pass regression architecture perform visual proprioception from a single external camera image, available even in the simplest manipulation settings? We explore several latent representations, including CNNs, VAEs, ViTs, and bags of uncalibrated fiducial markers, using fine-tuning techniques adapted to the limited data available. We evaluate the achievable accuracy through experiments on an inexpensive 6-DoF robot.
Authors: Peter Fletcher
Abstract: I introduce a formalism for representing the syntax of recursively structured graph-like patterns. It does not use production rules, like a conventional graph grammar, but represents the syntactic structure in a more direct and declarative way. The grammar and the pattern are both represented as networks, and parsing is seen as the construction of a homomorphism from the pattern to the grammar. The grammars can represent iterative, hierarchical and nested recursive structure in more than one dimension. This supports a highly parallel style of parsing, in which all aspects of pattern recognition (feature detection, segmentation, parsing, filling in missing symbols, top-down and bottom-up inference) are integrated into a single process, to exploit the synergy between them. The emphasis of this paper is on underlying theoretical issues, but I also give some example runs to illustrate the error-tolerant parsing of complex recursively structured patterns of 50-1000 symbols, involving variability in geometric relationships, blurry and indistinct symbols, overlapping symbols, cluttered images, and erased patches.