Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Sunday 23 November

Computer Vision · Cross-listed from cs.MM

DuoTeach: Dual Role Self-Teaching for Coarse-to-Fine Decision Coordination in Vision–Language Models

Coarse-to-fine path decision-making requires predicting a valid taxonomy path in which earlier decisions constrain later ones. However, existing benchmarks score each level independently, obscuring cross-level validity and consistency. To better align evaluation with this setting, we introduce a Joint Path Decision (JPD) protocol that requires predicting the full path in one call, together with Depth-Weighted Prefix Accuracy (DWPA), a metric family that measures path reliability with tunable emphasis on deeper levels. Under JPD, strong vision-language models (VLMs) frequently produce invalid parent-child pairs and brittle full-path predictions, suggesting that their failures stem not only from incomplete taxonomic knowledge but also from unstable cross-level decision coordination. To address this problem, we propose DuoTeach, a dual-role self-teaching distillation framework that requires no ground-truth labels and reuses the same pretrained VLM in two roles. Its Decision-Conditioned Rollout (DCR) generates more coherent teacher traces by conditioning each level on prior decisions, and distills this coordinated behavior into the student without additional test-time rollouts. Across multiple taxonomy-structured benchmarks and VLM base models, DuoTeach improves in-domain DWPA (alpha = 0.95) by up to 30.24 points and boosts zero-shot performance on unseen taxonomies from 17.17% to 43.66%. Further analyses attribute these gains to improved within-call multi-level decision coordination.
Read the full abstract

All authors Wei Yang, Yiran Zhu, Zilin Li, Xunjia Zhang, Jun Xia, Hongtao Wang

Computer Vision

ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering

This paper introduces ChineseVideoBench, a pioneering benchmark specifically designed for evaluating Multimodal Large Language Models (MLLMs) in Chinese Video Question Answering. The growing demand for sophisticated video analysis capabilities highlights the critical need for comprehensive, culturally-aware evaluation frameworks. ChineseVideoBench addresses this gap by providing a robust dataset and tailored evaluation metrics, enabling rigorous assessment of state-of-the-art MLLMs on complex Chinese video content. Specifically, ChineseVideoBench comprises 8 main classes and 12 sub-classes, encompassing tasks that demand both deep video understanding and nuanced Chinese linguistic and cultural awareness. Our empirical evaluations reveal that ChineseVideoBench presents a significant challenge to current MLLMs. Among the models assessed, Gemini 2.5 Pro achieves the highest performance with an overall score of 77.9%, while InternVL-38B emerges as the most competitive open-source model.
Read the full abstract

All authors Yuxiang Nie, Han Wang, Yongjie Ye, Haiyang Yu, Weitao Jia, Tao Zeng, Hao Feng, Xiang Fei, Yang Li, Xiaohui Lv, Guozhi Tang, Jingqun Tang, Jinghui Lu, Zehui Dai, Jiacong Wang, Dingkang Yang, An-Lan Wang, Can Huang

Computer Vision

Exploring Weak-to-Strong Generalization for CLIP-based Classification

Aligning large-scale commercial models with user intent is crucial to preventing harmful outputs. Current methods rely on human supervision but become impractical as model complexity increases. When models surpass human knowledge, providing accurate feedback becomes challenging and inefficient. A novel solution proposed recently is using a weaker model to supervise a stronger model. This concept leverages the ability of weaker models to perform evaluations, thereby reducing the workload on human supervisors. Previous work has shown the effectiveness of weak-to-strong generalization in the context of language-only models. Extending this concept to vision-language models leverages these insights, adapting the proven benefits to a multi-modal context. In our study, we explore weak-to-strong generalization for CLIP-based classification. We propose a method, class prototype learning (CPL), which aims to enhance the classification capabilities of the CLIP model, by learning more representative prototypes for each category. Our findings indicate that, despite using a simple loss function under weak supervision, CPL yields robust improvements in targeted scenarios, particularly when pretraining is limited. Extensive experiments demonstrate that our approach is effective under these settings, achieving a 3.67% improvement over strong baseline methods.
Read the full abstract

All authors Jinhao Li, Sarah M. Erfani, Lei Feng, James Bailey, Feng Liu

Computer Vision

SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation

We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constructing a compact semantic memory bank from multi-view 2D foundation model features and predicting discrete semantic indices alongside geometric and appearance attributes for each 3D Gaussian in a single pass, SegSplat efficiently imbues scenes with queryable semantics. Our experiments demonstrate that SegSplat achieves geometric fidelity comparable to state-of-the-art feed-forward 3D Gaussian Splatting methods while simultaneously enabling robust open-set semantic segmentation, crucially without requiring any per-scene optimization for semantic feature integration. This work represents a significant step towards practical, on-the-fly generation of semantically aware 3D environments, vital for advancing robotic interaction, augmented reality, and other intelligent systems.
Read the full abstract

All authors Peter Siegel, Federico Tombari, Marc Pollefeys, Daniel Barath

Computer Vision

Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection

Automatic X-ray prohibited items detection is vital for security inspection and has been widely studied. Traditional methods rely on visual modality, often struggling with complex threats. While recent studies incorporate language to guide single-view images, human inspectors typically use dual-view images in practice. This raises the question: can the second view provide constraints similar to a language modality? In this work, we introduce DualXrayBench, the first comprehensive benchmark for X-ray inspection that includes multiple views and modalities. It supports eight tasks designed to test cross-view reasoning. In DualXrayBench, we introduce a caption corpus consisting of 45,613 dual-view image pairs across 12 categories with corresponding captions. Building upon these data, we propose the Geometric (cross-view)-Semantic (cross-modality) Reasoner (GSR), a multimodal model that jointly learns correspondences between cross-view geometry and cross-modal semantics, treating the second-view images as a "language-like modality". To enable this, we construct the GSXray dataset, with structured Chain-of-Thought sequences: <top>, <side>, <conclusion>. Comprehensive evaluations on DualXrayBench demonstrate that GSR achieves significant improvements across all X-ray tasks, offering a new perspective for real-world X-ray inspection.
Read the full abstract

All authors Chuang Peng, Renshuai Tao, Zhongwei Ren, Xianglong Liu, Yunchao Wei

Computer Vision

ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access

Text-to-video generation has surged in interest since Sora, yet open-source models still face a data bottleneck: there is no large, high-quality, easily obtainable video-text corpus. Existing public datasets typically require manual YouTube crawling, which yields low usable volume due to link rot and access limits, and raises licensing uncertainty. This work addresses this challenge by introducing ViMix-14M, a curated multi-source video-text dataset of around 14 million pairs that provides crawl-free, download-ready access and long-form, high-quality captions tightly aligned to video. ViMix-14M is built by merging diverse open video sources, followed by unified de-duplication and quality filtering, and a multi-granularity, ground-truth-guided re-captioning pipeline that refines descriptions to better match actions, scenes, and temporal structure. We evaluate the dataset by multimodal retrieval, text-to-video generation, and video question answering tasks, observing consistent improvements over counterpart datasets. We hope this work can help removing the key barrier to training and fine-tuning open-source video foundation models, and provide insights of building high-quality and generalizable video-text datasets.
Read the full abstract

All authors Timing Yang, Sucheng Ren, Alan Yuille, Feng Wang

Computer Vision

RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models

Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we systematically investigate Mamba's representational properties and make three primary contributions. First, we theoretically analyze Mamba's relationship to Softmax and Linear Attention, confirming that it can be viewed as a low-rank approximation of Softmax Attention and thereby bridging the representational gap between Softmax and Linear forms. Second, we introduce a novel binary segmentation metric for activation map evaluation, extending qualitative assessments to a quantitative measure that demonstrates Mamba's capacity to model long-range dependencies. Third, by leveraging DINO for self-supervised pretraining, we obtain clearer activation maps than those produced by standard supervised approaches, highlighting Mamba's potential for interpretability. Notably, our model also achieves a 78.5 percent linear probing accuracy on ImageNet, underscoring its strong performance. We hope this work can provide valuable insights for future investigations of Mamba-based vision architectures.
Read the full abstract

All authors Timing Yang, Guoyizhe Wei, Alan Yuille, Feng Wang

Computer Vision

Synthetic Curriculum Reinforces Compositional Text-to-Image Generation

Text-to-Image (T2I) generation has long been an open problem, with compositional synthesis remaining particularly challenging. This task requires accurate rendering of complex scenes containing multiple objects that exhibit diverse attributes as well as intricate spatial and semantic relationships, demanding both precise object placement and coherent inter-object interactions. In this paper, we propose a novel compositional curriculum reinforcement learning framework named CompGen that addresses compositional weakness in existing T2I models. Specifically, we leverage scene graphs to establish a novel difficulty criterion for compositional ability and develop a corresponding adaptive Markov Chain Monte Carlo graph sampling algorithm. This difficulty-aware approach enables the synthesis of training curriculum data that progressively optimize T2I models through reinforcement learning. We integrate our curriculum learning approach into Group Relative Policy Optimization (GRPO) and investigate different curriculum scheduling strategies. Our experiments reveal that CompGen exhibits distinct scaling curves under different curriculum scheduling strategies, with easy-to-hard and Gaussian sampling strategies yielding superior scaling performance compared to random sampling. Extensive experiments demonstrate that CompGen significantly enhances compositional generation capabilities for both diffusion-based and auto-regressive T2I models, highlighting its effectiveness in improving the compositional T2I generation systems.
Read the full abstract

All authors Shijian Wang, Runhao Fu, Siyi Zhao, Qingqin Zhan, Xingjian Wang, Jiarui Jin, Yuan Lu, Hanqian Wu, Cunjian Chen

Computer Vision

MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models

Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a novel approach to address this gap by translating physical-world context cues into interpretable representations aligned with VLM perception, comprehension, and reasoning. We introduce MASS, a model-agnostic approach that injects spatiotemporal signals into the VLM language space via depth-based 3D encoding and visual grounding, coupled with a motion tracker for object dynamics. We also contribute a comprehensive benchmark, MASS-Bench, consisting of 4,350 real-world and AIGC videos and 8,361 free-form video question-answering pairs focused on physics-related comprehension tasks, with detailed annotations including visual detections and grounding over sub-segments, as well as full-sequence 3D motion tracking of entities. To strengthen cross-modal alignment and reasoning, we apply reinforcement fine-tuning to MASS. Experiments and ablations show that our refined VLMs outperform comparable baselines, larger models, and prior state-of-the-art models, achieving performance comparable to closed-source state-of-the-art VLMs, with only a 2% gap to Gemini-2.5-Flash on physics reasoning and comprehension.
Read the full abstract

All authors Xiyang Wu, Zongxia Li, Jihui Jin, Guangyao Shi, Gouthaman KV, Vishnu Raj, Nilotpal Sinha, Jingxi Chen, Fan Du, Dinesh Manocha

Computer Vision

MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer

3D pose transfer aims to transfer the pose-style of a source mesh to a target character while preserving both the target's geometry and the source's pose characteristic. Existing methods are largely restricted to characters with similar structures and fail to generalize to category-free settings (e.g., transferring a humanoid's pose to a quadruped). The key challenge lies in the structural and transformation diversity inherent in distinct character types, which often leads to mismatched regions and poor transfer quality. To address these issues, we first construct a million-scale pose dataset across hundreds of distinct characters. We further propose MimiCAT, a cascade-transformer model designed for category-free 3D pose transfer. Instead of relying on strict one-to-one correspondence mappings, MimiCAT leverages semantic keypoint labels to learn a novel soft correspondence that enables flexible many-to-many matching across characters. The pose transfer is then formulated as a conditional generation process, in which the source transformations are first projected onto the target through soft correspondence matching and subsequently refined using shape-conditioned representations. Extensive qualitative and quantitative experiments demonstrate that MimiCAT generalizes plausible poses across diverse character morphologies, surpassing prior approaches restricted to narrow-category transfer (e.g., humanoid-to-humanoid).
Read the full abstract

All authors Zenghao Chai, Chen Tang, Yongkang Wong, Xulei Yang, Mohan Kankanhalli

Computer Vision

Alias-free 4D Gaussian Splatting

Existing dynamic scene reconstruction methods based on Gaussian Splatting enable real-time rendering and generate realistic images. However, adjusting the camera's focal length or the distance between Gaussian primitives and the camera to modify rendering resolution often introduces strong artifacts, stemming from the frequency constraints of 4D Gaussians and Gaussian scale mismatch induced by the 2D dilated filter. To address this, we derive a maximum sampling frequency formulation for 4D Gaussian Splatting and introduce a 4D scale-adaptive filter and scale loss, which flexibly regulates the sampling frequency of 4D Gaussian Splatting. Our approach eliminates high-frequency artifacts under increased rendering frequencies while effectively reducing redundant Gaussians in multi-view video reconstruction. We validate the proposed method through monocular and multi-view video reconstruction experiments.Ours project page: https://4d-alias-free.github.io/4D-Alias-free/
Read the full abstract

All authors Zilong Chen, Huan-ang Gao, Delin Qu, Haohan Chi, Hao Tang, Kai Zhang, Hao Zhao

Computer Vision

TRANSPORTER: Transferring Visual Semantics from VLM Manifolds

How do video understanding models acquire their answers? Although current Vision Language Models (VLMs) reason over complex scenes with diverse objects, action performances, and scene dynamics, understanding and controlling their internal processes remains an open challenge. Motivated by recent advancements in text-to-video (T2V) generative models, this paper introduces a logits-to-video (L2V) task alongside a model-independent approach, TRANSPORTER, to generate videos that capture the underlying rules behind VLMs' predictions. Given the high-visual-fidelity produced by T2V models, TRANSPORTER learns an optimal transport coupling to VLM's high-semantic embedding spaces. In turn, logit scores define embedding directions for conditional video generation. TRANSPORTER generates videos that reflect caption changes over diverse object attributes, action adverbs, and scene context. Quantitative and qualitative evaluations across VLMs demonstrate that L2V can provide a fidelity-rich, novel direction for model interpretability that has not been previously explored.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

Enhancing UAV Search under Occlusion using Next Best View Planning

Search and rescue missions are often critical following sudden natural disasters or in high-risk environmental situations. The most challenging search and rescue missions involve difficult-to-access terrains, such as dense forests with high occlusion. Deploying unmanned aerial vehicles for exploration can significantly enhance search effectiveness, facilitate access to challenging environments, and reduce search time. However, in dense forests, the effectiveness of unmanned aerial vehicles depends on their ability to capture clear views of the ground, necessitating a robust search strategy to optimize camera positioning and perspective. This work presents an optimized planning strategy and an efficient algorithm for the next best view problem in occluded environments. Two novel optimization heuristics, a geometry heuristic, and a visibility heuristic, are proposed to enhance search performance by selecting optimal camera viewpoints. Comparative evaluations in both simulated and real-world settings reveal that the visibility heuristic achieves greater performance, identifying over 90% of hidden objects in simulated forests and offering 10% better detection rates than the geometry heuristic. Additionally, real-world experiments demonstrate that the visibility heuristic provides better coverage under the canopy, highlighting its potential for improving search and rescue missions in occluded environments.
Read the full abstract

All authors Sigrid Helene Strand, Thomas Wiedemann, Bram Burczek, Dmitriy Shutin

Computer Vision

MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference

Recent advances in AIGC (Artificial Intelligence Generated Content) models have enabled significant progress in image and video generation. However, users still struggle to obtain content that aligns with their preferences due to the difficulty of crafting detailed prompts and the lack of mechanisms to retain their preferences. To address these challenges, we construct UniPrefer-100K, a large-scale dataset comprising images, videos, and associated text that describes the styles users tend to prefer. Based on UniPrefer-100K, we propose MagicWand, a universal generation and evaluation agent that enhances prompts based on user preferences, leverages advanced generation models for high-quality content, and applies preference-aligned evaluation and refinement. In addition, we introduce UniPreferBench, the first large-scale benchmark with over 120K annotations for assessing user preference alignment across diverse AIGC tasks. Experiments on UniPreferBench demonstrate that MagicWand consistently generates content and evaluations that are well aligned with user preferences across a wide range of scenarios.
Read the full abstract

All authors Zitong Xu, Dake Shen, Yaosong Du, Kexiang Hao, Jinghan Huang, Xiande Huang

Computer Vision

FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement

Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal consistency, spatial fidelity, and illumination naturalness. To address these issues, we introduce FlowPortal, a novel training-free flow-based video relighting framework. Our core innovation is a Residual-Corrected Flow mechanism that transforms a standard flow-based model into an editing model, guaranteeing perfect reconstruction when input conditions are identical and enabling faithful relighting when they differ, resulting in high structural consistency. This is further enhanced by a Decoupled Condition Design for precise lighting control and a High-Frequency Transfer mechanism for detail preservation. Additionally, a masking strategy isolates foreground relighting from background pure generation process. Experiments demonstrate that FlowPortal achieves superior performance in temporal coherence, structural preservation, and lighting realism, while maintaining high efficiency. Project Page: https://gaowenshuo.github.io/FlowPortalProject/.
Read the full abstract

All authors Wenshuo Gao, Junyi Fan, Jiangyue Zeng, Shuai Yang

Computer Vision

A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles

With the proliferation of low altitude unmanned aerial vehicles (UAVs), visual multi-object tracking is becoming a critical security technology, demanding significant robustness even in complex environmental conditions. However, tracking UAVs using a single visual modality often fails in challenging scenarios, such as low illumination, cluttered backgrounds, and rapid motion. Although multi-modal multi-object UAV tracking is more resilient, the development of effective solutions has been hindered by the absence of dedicated public datasets. To bridge this gap, we release MM-UAV, the first large-scale benchmark for Multi-Modal UAV Tracking, integrating three key sensing modalities, e.g. RGB, infrared (IR), and event signals. The dataset spans over 30 challenging scenarios, with 1,321 synchronised multi-modal sequences, and more than 2.8 million annotated frames. Accompanying the dataset, we provide a novel multi-modal multi-UAV tracking framework, designed specifically for UAV tracking applications and serving as a baseline for future research. Our framework incorporates two key technical innovations, e.g. an offset-guided adaptive alignment module to resolve spatio mismatches across sensors, and an adaptive dynamic fusion module to balance complementary information conveyed by different modalities. Furthermore, to overcome the limitations of conventional appearance modelling in multi-object tracking, we introduce an event-enhanced association mechanism that leverages motion cues from the event modality for more reliable identity maintenance. Comprehensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art methods. To foster further research in multi-modal UAV tracking, both the dataset and source code will be made publicly available at https://xuefeng-zhu5.github.io/MM-UAV/.
Read the full abstract

All authors Tianyang Xu, Jinjie Gu, Xuefeng Zhu, XiaoJun Wu, Josef Kittler

Computer Vision · Cross-listed from cs.LG

Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection

Spatial transcriptomics (ST) is a novel technology that enables the observation of gene expression at the resolution of individual spots within pathological tissues. ST quantifies the expression of tens of thousands of genes in a tissue section; however, heavy observational noise is often introduced during measurement. In prior studies, to ensure meaningful assessment, both training and evaluation have been restricted to only a small subset of highly variable genes, and genes outside this subset have also been excluded from the training process. However, since there are likely co-expression relationships between genes, low-expression genes may still contribute to the estimation of the evaluation target. In this paper, we propose $Auxiliary \ Gene \ Learning$ (AGL) that utilizes the benefit of the ignored genes by reformulating their expression estimation as auxiliary tasks and training them jointly with the primary tasks. To effectively leverage auxiliary genes, we must select a subset of auxiliary genes that positively influence the prediction of the target genes. However, this is a challenging optimization problem due to the vast number of possible combinations. To overcome this challenge, we propose Prior-Knowledge-Based Differentiable Top-$k$ Gene Selection via Bi-level Optimization (DkGSB), a method that ranks genes by leveraging prior knowledge and relaxes the combinatorial selection problem into a differentiable top-$k$ selection problem. The experiments confirm the effectiveness of incorporating auxiliary genes and show that the proposed method outperforms conventional auxiliary task learning approaches.
Read the full abstract

All authors Kaito Shiku, Kazuya Nishimura, Shinnosuke Matsuo, Yasuhiro Kojima, Ryoma Bise

Computer Vision

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with image regions-while their generative counterpart, linguistic-embedded layout-grounded generation (LELG) for layout-controllable multi-instance generation, remains underexplored and limits precise compositional control. We present ConsistCompose, a unified multimodal framework that embeds layout coordinates directly into language prompts, enabling layout-controlled multi-instance image generation from Interleaved Image-Text within a single generative interface. We further construct ConsistCompose3M, a 3.4M multi-instance generation dataset with layout and identity annotations (2.6M text-guided and 0.8M image-guided data pairs) that provides large-scale supervision for layout-conditioned generation. Within this framework, LELG is instantiated through instance-coordinate binding prompts and coordinate-aware classifier-free guidance, which translate linguistic layout cues into precise spatial control without task-specific branches. Experiments on COCO-Position and MS-Bench show that ConsistCompose substantially improves spatial accuracy over layout-controlled baselines while preserving identity fidelity and competitive general multimodal understanding, establishing a unified paradigm for layout-controllable multimodal image generation.
Read the full abstract

All authors Xuanke Shi, Boxuan Li, Xiaoyang Han, Zhongang Cai, Lei Yang, Quan Wang, Dahua Lin

Computer Vision

SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posters

Scientific posters play a vital role in academic communication by presenting ideas through visual summaries. Analyzing reading order and parent-child relations of posters is essential for building structure-aware interfaces that facilitate clear and accurate understanding of research content. Despite their prevalence in academic communication, posters remain underexplored in structural analysis research, which has primarily focused on papers. To address this gap, we constructed SciPostLayoutTree, a dataset of approximately 8,000 posters annotated with reading order and parent-child relations. Compared to an existing structural analysis dataset, SciPostLayoutTree contains more instances of spatially challenging relations, including upward, horizontal, and long-distance relations. As a solution to these challenges, we develop Layout Tree Decoder, which incorporates visual features as well as bounding box features including position and category information. The model also uses beam search to predict relations while capturing sequence-level plausibility. Experimental results demonstrate that our model improves the prediction accuracy for spatially challenging relations and establishes a solid baseline for poster structure analysis. The dataset is publicly available at https://huggingface.co/datasets/omron-sinicx/scipostlayouttree. The code is also publicly available at https://github.com/omron-sinicx/scipostlayouttree.
Read the full abstract

Computer Vision

General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification

The accurate identification of brain tumors from magnetic resonance imaging (MRI) is essential for timely diagnosis and effective therapeutic intervention. While deep convolutional neural networks (CNNs), particularly those pre-trained on extensive datasets, have shown considerable promise in medical image analysis, a key question arises when working with limited data: do models pre-trained on specialized medical image repositories outperform those pre-trained on diverse, general-domain datasets? This research presents a comparative analysis of three distinct pre-trained CNN architectures for brain tumor classification: RadImageNet DenseNet121, which leverages pre-training on medical-domain data, alongside two modern general-purpose networks, EfficientNetV2S and ConvNeXt-Tiny. All models were trained and fine-tuned under uniform experimental conditions using a modestly sized brain MRI dataset to maintain consistency in evaluation. The experimental outcomes indicate that ConvNeXt-Tiny delivered the best performance, achieving 93% test accuracy, followed by EfficientNetV2S at 85%. In contrast, RadImageNet DenseNet121 attained only 68% accuracy and exhibited higher loss, indicating limited generalization capability despite its domain-specific pre-training. These observations imply that pre-training on medical-domain data does not necessarily guarantee superior performance in data-scarce scenarios. Conversely, contemporary general-purpose CNNs with deeper architectures, pre-trained on large-scale diverse datasets, may offer more effective transfer learning for specialized diagnostic tasks in medical imaging.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

Learning Visually Interpretable Oscillator Networks for Soft Continuum Robots from Video

Learning soft continuum robot (SCR) dynamics from video offers flexibility but existing methods lack interpretability or rely on prior assumptions. Model-based approaches require prior knowledge and manual design. We bridge this gap by introducing: (1) The Attention Broadcast Decoder (ABCD), a plug-and-play module for autoencoder-based latent dynamics learning that generates pixel-accurate attention maps localizing each latent dimension's contribution while filtering static backgrounds, enabling visual interpretability via spatially grounded latents and on-image overlays. (2) Visual Oscillator Networks (VONs), a 2D latent oscillator network coupled to ABCD attention maps for on-image visualization of learned masses, coupling stiffness, and forces, thereby enabling mechanical interpretability. We validate our approach on single- and double-segment SCRs, demonstrating that ABCD-based models significantly improve multi-step prediction accuracy with 5.8x error reduction for Koopman operators and 3.5x for oscillator networks on a two-segment robot. VONs autonomously discover a chain structure of oscillators. This fully data-driven approach yields compact, mechanically interpretable models with potential relevance for future control applications.
Read the full abstract

All authors Henrik Krauss, Johann Licher, Naoya Takeishi, Annika Raatz, Takehisa Yairi

Computer Vision

Optimal Pose Guidance for Stereo Calibration in 3D Deformation Measurement

Stereo optical measurement techniques, such as digital image correlation (DIC), are widely used in 3D deformation measurement as non-contact, full-field measurement methods, in which stereo calibration is a crucial step. However, current stereo calibration methods lack intuitive optimal pose guidance, leading to inefficiency and suboptimal accuracy in deformation measurements. The aim of this study is to develop an interactive calibration framework that automatically generates the next optimal pose, enabling high-accuracy stereo calibration for 3D deformation measurement. We propose a pose optimization method that introduces joint optimization of relative and absolute extrinsic parameters, with the minimization of the covariance matrix trace adopted as the loss function to solve for the next optimal pose. Integrated with this method is a user-friendly graphical interface, which guides even non-expert users to capture qualified calibration images. Our proposed method demonstrates superior efficiency (requiring fewer images) and accuracy (demonstrating lower measurement errors) compared to random pose, while maintaining robustness across varying FOVs. In the thermal deformation measurement tests on an S-shaped specimen, the results exhibit high agreement with finite element analysis (FEA) simulations in both deformation magnitude and evolutionary trends. We present a pose guidance method for high-precision stereo calibration in 3D deformation measurement. The simulation experiments, real-world experiments, and thermal deformation measurement applications all demonstrate the significant application potential of our proposed method in the field of 3D deformation measurement. Keywords: Stereo calibration, Optimal pose guidance, 3D deformation measurement, Digital image correlation
Read the full abstract

All authors Dongcai Tan, Shunkun Liang, Bin Li, Banglei Guan, Ang Su, Yuan Lin, Dapeng Zhang, Minggang Wan, Zibin Liu, Chenglong Wang, Jiajian Zhu, Zhang Li, Yang Shang, Qifeng Yu

Computer Vision

Stro-VIGRU: Defining the Vision Recurrent-Based Baseline Model for Brain Stroke Classification

Stroke majorly causes death and disability worldwide, and early recognition is one of the key elements of successful treatment of the same. It is common to diagnose strokes using CT scanning, which is fast and readily available, however, manual analysis may take time and may result in mistakes. In this work, a pre-trained Vision Transformer-based transfer learning framework is proposed for the early identification of brain stroke. A few of the encoder blocks of the ViT model are frozen, and the rest are allowed to be fine-tuned in order to learn brain stroke-specific features. The features that have been extracted are given as input to a single-layer Bi-GRU to perform classification. Class imbalance is handled by data augmentation. The model has achieved 94.06% accuracy in classifying brain stroke from the Stroke Dataset.
Read the full abstract

All authors Subhajeet Das, Pritam Paul, Rohit Bahadur, Sohan Das

Computer Vision

ScriptViT: Vision Transformer-Based Personalized Handwriting Generation

Styled handwriting generation aims to synthesize handwritten text that looks both realistic and aligned with a specific writer's style. While recent approaches involving GAN, transformer and diffusion-based models have made progress, they often struggle to capture the full spectrum of writer-specific attributes, particularly global stylistic patterns that span long-range spatial dependencies. As a result, capturing subtle writer-specific traits such as consistent slant, curvature or stroke pressure, while keeping the generated text accurate is still an open problem. In this work, we present a unified framework designed to address these limitations. We introduce a Vision Transformer-based style encoder that learns global stylistic patterns from multiple reference images, allowing the model to better represent long-range structural characteristics of handwriting. We then integrate these style cues with the target text using a cross-attention mechanism, enabling the system to produce handwritten images that more faithfully reflect the intended style. To make the process more interpretable, we utilize Salient Stroke Attention Analysis (SSAA), which reveals the stroke-level features the model focuses on during style transfer. Together, these components lead to handwriting synthesis that is not only more stylistically coherent, but also easier to understand and analyze.
Read the full abstract

Computer Vision

DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition

Large Vision Language Models (LVLMs) possess extensive text knowledge but struggles to utilize this knowledge for fine-grained image recognition, often failing to differentiate between visually similar categories. Existing fine-tuning methods using Reinforcement Learning (RL) with exact-match reward signals are often brittle, encourage memorization of training categories, and fail to elicit differential reasoning needed for generalization to unseen classes. To address this, we propose $\textbf{DiVE-k}$, $\textbf{Di}$fferential $\textbf{V}$isual r$\textbf{E}$asoning using top-$\textbf{k}$ generations, framework that leverages model's own top-k predictions as a training signal. For each training image, DiVE-k creates a multiple-choice question from the model's top-k outputs and uses RL to train the model to select the correct answer. This approach requires the model to perform fine-grained differential reasoning among plausible options and provides a simple, verifiable reward signal that mitigates memorization and improves generalization. Experiments on five standard fine-grained datasets show that our method significantly outperforms existing approaches. In the standard base-to-novel generalization setting, DiVE-k surpasses the QWEN2.5-VL-7B and ViRFT by 10.04% and 6.16% on the Harmonic Mean metric, respectively. Further experiments show similar gains in mixed-domain and few-shot scenarios. Our code is available $\href{https://github.com/raja-kumar/DiVE-k}{here}$
Read the full abstract

Computer Vision

SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes

3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times. In this paper, we propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction. To maintain global consistency in large-scale scenes, SwiftVGGT performs loop closure without relying on the external Visual Place Recognition (VPR) model. This removes redundant computation and enables accurate reconstruction over kilometer-scale environments. Furthermore, we propose a simple yet effective point sampling method to align neighboring chunks using a single Sim(3)-based Singular Value Decomposition (SVD) step. This eliminates the need for the Iteratively Reweighted Least Squares (IRLS) optimization commonly used in prior work, leading to substantial speed-ups. We evaluate SwiftVGGT on multiple datasets and show that it achieves state-of-the-art reconstruction quality while requiring only 33% of the inference time of recent VGGT-based large-scale reconstruction approaches.
Read the full abstract

All authors Jungho Lee, Minhyeok Lee, Sunghun Yang, Minseok Kang, Sangyoun Lee

Computer Vision · Cross-listed from cs.LG

TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis

Accurately modeling the relationship between perturbations, transcriptional responses, and phenotypic changes is essential for building an AI Virtual Cell (AIVC). However, existing methods typically constrained to modeling direct associations, such as Perturbation $\rightarrow$ RNA or Perturbation $\rightarrow$ Morphology, overlook the crucial causal link from RNA to morphology. To bridge this gap, we propose TRIDENT, a cascade generative framework that synthesizes realistic cellular morphology by conditioning on both the perturbation and the corresponding gene expression profile. To train and evaluate this task, we construct MorphoGene, a new dataset pairing L1000 gene expression with Cell Painting images for 98 compounds. TRIDENT significantly outperforms state-of-the-art approaches, achieving up to 7-fold improvement with strong generalization to unseen compounds. In a case study on docetaxel, we validate that RNA-guided synthesis accurately produces the corresponding phenotype. An ablation study further confirms that this RNA conditioning is essential for the model's high fidelity. By explicitly modeling transcriptome-phenome mapping, TRIDENT provides a powerful in silico tool and moves us closer to a predictive virtual cell.
Read the full abstract

All authors Rui Peng, Ziru Liu, Lingyuan Ye, Yuxing Lu, Boxin Shi, Jinzhuo Wang

Computer Vision

RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System

Current roadside perception systems mainly focus on instance-level perception, which fall short in enabling interaction via natural language and reasoning about traffic behaviors in context. To bridge this gap, we introduce RoadSceneVQA, a large-scale and richly annotated visual question answering (VQA) dataset specifically tailored for roadside scenarios. The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions, targeting not only object attributes but also the intent, legality, and interaction patterns of traffic participants. RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning, grounded in real-world traffic rules and contextual dependencies. To fully exploit the reasoning potential of Multi-modal Large Language Models (MLLMs), we further propose CogniAnchor Fusion (CAF), a vision-language fusion module inspired by human-like scene anchoring mechanisms. Moreover, we propose the Assisted Decoupled Chain-of-Thought (AD-CoT) to enhance the reasoned thinking via CoT prompting and multi-task learning. Based on the above, we propose the baseline model RoadMind. Experiments on RoadSceneVQA and CODA-LM benchmark show that the pipeline consistently improves both reasoning accuracy and computational efficiency, allowing the MLLM to achieve state-of-the-art performance in structural traffic perception and reasoning tasks.
Read the full abstract

All authors Runwei Guan, Rongsheng Hu, Shangshu Chen, Ningyuan Xiao, Xue Xia, Jiayang Liu, Beibei Chen, Ziren Tang, Ningwei Ouyang, Shaofeng Liang, Yuxuan Fan, Wanjie Sun, Yutao Yue

Computer Vision

Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation

Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation for novel domains relies on two-stage pipelines: Adapt-then-Distill or Distill-then-Adapt. However, both add design complexity and often degrade quality or diversity. We introduce Uni-DAD, a single-stage pipeline that unifies DM distillation and adaptation. It couples two training signals: (i) a dual-domain distribution-matching distillation (DMD) objective that guides the student toward the distributions of the source teacher and a target teacher, and (ii) a multi-head generative adversarial network (GAN) loss that encourages target realism across multiple feature scales. The source domain distillation preserves diverse source knowledge, while the multi-head GAN stabilizes training and reduces overfitting, especially in few-shot regimes. The inclusion of a target teacher facilitates adaptation to more structurally distant domains. We evaluate Uni-DAD on two comprehensive benchmarks for few-shot image generation (FSIG) and subject-driven personalization (SDP) using diffusion backbones. It delivers better or comparable quality to state-of-the-art (SoTA) adaptation methods even with less than 4 sampling steps, and often surpasses two-stage pipelines in quality and diversity. Code: https://github.com/yaramohamadi/uni-DAD.
Read the full abstract

All authors Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri, Eric Granger

Computer Vision · Cross-listed from cs.LG

From Tables to Signals: Revealing Spectral Adaptivity in TabPFN

Task-agnostic tabular foundation models such as TabPFN have achieved impressive performance on tabular learning tasks, yet the origins of their inductive biases remain poorly understood. In this work, we study TabPFN through the lens of signal reconstruction and provide the first frequency-based analysis of its in-context learning behavior. We show that TabPFN possesses a broader effective frequency capacity than standard ReLU-MLPs, even without hyperparameter tuning. Moreover, unlike MLPs whose spectra evolve primarily over training epochs, we find that TabPFN's spectral capacity adapts directly to the number of samples provided in-context, a phenomenon we term Spectral Adaptivity. We further demonstrate that positional encoding modulates TabPFN's frequency response, mirroring classical results in implicit neural representations. Finally, we show that these properties enable TabPFN to perform training-free and hyperparameter-free image denoising, illustrating its potential as a task-agnostic implicit model. Our analysis provides new insight into the structure and inductive biases of tabular foundation models and highlights their promise for broader signal reconstruction tasks.
Read the full abstract

All authors Jianqiao Zheng, Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Simon Lucey