Peer Revenue Play credits. Real papers.

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)

Saturday 8 November

Computer Vision

Cross-Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptation

Alzheimer's disease (AD) is a prevalent neurodegenerative disorder for which early detection is critical. Handwriting, which can be disrupted by subtle motor and cognitive decline, provides a non-invasive and cost-effective window for AD screening. Existing handwriting-based AD studies mostly rely on online trajectories and hand-crafted features, while the influence of handwriting task type on diagnostic performance and cross-task generalization remains underexplored. Meanwhile, large-scale vision–language models have demonstrated strong transfer and adaptation ability in natural-image anomaly detection and several medical modalities, such as chest X-ray and brain MRI. However, handwriting-based disease detection remains unexplored within this paradigm. To address this gap, we introduce a lightweight Cross-Layer Fusion Adapter (CLFA) framework that repurposes Contrastive Language–Image Pre-training (CLIP) for handwriting-based AD screening. CLFA inserts multi-level adapters into a frozen visual encoder, combining cross-layer feature fusion with depthwise 2D convolution on patch grids to capture both local stroke irregularities and higher-level handwriting structure. This design progressively aligns pretrained vision–language representations with AD-related handwriting cues and supports transfer from supervised source tasks to task-disjoint unseen target tasks. On the Darwin dataset, under the subject-disjoint cross-task protocol, averaged over all 600 task-disjoint source-target pairs, CLFA achieves 74.63% AUC, 74.85% accuracy, and 73.72% F1 score, outperforming the best competing model by 2.15, 1.79, and 1.87 percentage points, respectively.
Read the full abstract

Computer Vision · Cross-listed from eess.IV

Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines

Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision technology into real-world applications. However, most neural network-based ICM frameworks operate at a fixed rate, thus requiring individual training for each target bitrate. This limitation may restrict their practical usage. Existing variable rate image compression approaches mitigate this issue but often rely on additional training, which increases computational costs and complicates deployment. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free framework for quantization strength control which enables flexible bitrate adjustment. By exploiting the scale parameter predicted by the hyperprior network, the proposed method adaptively modulates quantization step sizes across both channel and spatial dimensions. This allows the model to preserve semantically important regions while coarsely quantizing less critical areas. Our architectural design further enables continuous bitrate control through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate baseline. The code is available at https://github.com/qwert-top/AQVR-ICM.
Read the full abstract

Computer Vision

TYrPPG: Uncomplicated and Enhanced Learning Capability rPPG for Remote Heart Rate Estimation

Remote photoplethysmography (rPPG) can remotely extract physiological signals from RGB video, which has many advantages in detecting heart rate, such as low cost and no invasion to patients. The existing rPPG model is usually based on the transformer module, which has low computation efficiency. Recently, the Mamba model has garnered increasing attention due to its efficient performance in natural language processing tasks, demonstrating potential as a substitute for transformer-based algorithms. However, the Mambaout model and its variants prove that the SSM module, which is the core component of the Mamba model, is unnecessary for the vision task. Therefore, we hope to prove the feasibility of using the Mambaout-based module to remotely learn the heart rate. Specifically, we propose a novel rPPG algorithm called uncomplicated and enhanced learning capability rPPG (TYrPPG). This paper introduces an innovative gated video understanding block (GVB) designed for efficient analysis of RGB videos. Based on the Mambaout structure, this block integrates 2D-CNN and 3D-CNN to enhance video understanding for analysis. In addition, we propose a comprehensive supervised loss function (CSL) to improve the model's learning capability, along with its weakly supervised variants. The experiments show that our TYrPPG can achieve state-of-the-art performance in commonly used datasets, indicating its prospects and superiority in remote heart rate estimation. The source code is available at https://github.com/Taixi-CHEN/TYrPPG.
Read the full abstract

Computer Vision

Hilbert-Guided Sparse Local Attention

The quadratic compute and memory costs of global self-attention severely limit its use in high-resolution images. Local attention reduces complexity by restricting attention to neighborhoods. Block-sparse kernels can further improve the efficiency of local attention, but conventional local attention patterns often fail to deliver significant speedups because tokens within a window are not contiguous in the 1D sequence. This work proposes a novel method for constructing windows and neighborhoods based on the Hilbert curve. Image tokens are first reordered along a Hilbert curve, and windows and neighborhoods are then formed on the reordered 1D sequence. From a block-sparse perspective, this strategy significantly increases block sparsity and can be combined with existing block-sparse kernels to improve the efficiency of 2D local attention. Experiments show that the proposed Hilbert Window Attention and Hilbert Slide Attention can accelerate window attention and slide attention by about $4\times$ and $18\times$, respectively. To assess practicality, the strategy is instantiated as the Hilbert Window Transformer and the Hilbert Neighborhood Transformer, both of which achieve end-to-end speedups with minimal accuracy loss. Overall, combining Hilbert-guided local attention with block-sparse kernels offers a general and practical approach to enhancing the efficiency of 2D local attention for images.
Read the full abstract

Computer Vision

LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting

End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains challenging. We identify the primary bottleneck as the lack of a reliable and efficient text detection method. To address this, we propose a novel parameterized text shape representation based on low-rank approximation for precise detection and a triple assignment detection head for fast inference. Specifically, unlike current data-irrelevant shape representation methods, we exploit shape correlations among labeled text boundaries to construct a robust low-rank subspace. By minimizing an $\ell_1$-norm objective, we extract orthogonal vectors that capture the intrinsic text shape from noisy annotations, enabling precise reconstruction via the linear combination of only a few basis vectors. Next, the triple assignment scheme decouples training complexity from inference speed. It utilizes a deep sparse branch to guide an ultra-lightweight inference branch, while a dense branch provides rich parallel supervision. Building upon these advancements, we integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++, capable of accurately and efficiently spotting arbitrary-shaped text. Extensive experiments on challenging benchmarks demonstrate the superiority of LRANet++ compared to state-of-the-art methods. Code is available at: https://github.com/ychensu/LRANet-PP.
Read the full abstract

All authors Yuchen Su, Zhineng Chen, Yongkun Du, Zuxuan Wu, Hongtao Xie, Yu-Gang Jiang

Computer Vision

MACMD: Multi-dilated Contextual Attention and Channel Mixer Decoding for Medical Image Segmentation

Medical image segmentation faces challenges due to variations in anatomical structures. While convolutional neural networks (CNNs) effectively capture local features, they struggle with modeling long-range dependencies. Transformers mitigate this issue with self-attention mechanisms but lack the ability to preserve local contextual information. State-of-the-art models primarily follow an encoder-decoder architecture, achieving notable success. However, two key limitations remain: (1) Shallow layers, which are closer to the input, capture fine-grained details but suffer from information loss as data propagates through deeper layers. (2) Inefficient integration of local details and global context between the encoder and decoder stages. To address these challenges, we propose the MACMD-based decoder, which enhances attention mechanisms and facilitates channel mixing between encoder and decoder stages via skip connections. This design leverages hierarchical dilated convolutions, attention-driven modulation, and a cross channel-mixing module to capture long-range dependencies while preserving local contextual details, essential for precise medical image segmentation. We evaluated our approach using multiple transformer encoders on both binary and multi-organ segmentation tasks. The results demonstrate that our method outperforms state-of-the-art approaches in terms of Dice score and computational efficiency, highlighting its effectiveness in achieving accurate and robust segmentation performance. The code available at https://github.com/lalitmaurya47/MACMD
Read the full abstract

Computer Vision

Position-Prior-Guided Network for System Matrix Super-Resolution in Magnetic Particle Imaging

Magnetic Particle Imaging (MPI) is a novel medical imaging modality. One of the established methods for MPI reconstruction is based on the System Matrix (SM). However, the calibration of the SM is often time-consuming and requires repeated measurements whenever the system parameters change. Current methodologies utilize deep learning-based super-resolution (SR) techniques to expedite SM calibration; nevertheless, these strategies do not fully exploit physical prior knowledge associated with the SM, such as symmetric positional priors. Consequently, we integrated positional priors into existing frameworks for SM calibration. Underpinned by theoretical justification, we empirically validated the efficacy of incorporating positional priors through experiments involving both 2D and 3D SM SR methods.
Read the full abstract

All authors Xuqing Geng, Lei Su, Zhongwei Bian, Zewen Sun, Jiaxuan Wen, Jie Tian, Yang Du

Computer Vision

TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation

Unsupervised domain adaptation (UDA) for medical image segmentation remains challenging due to substantial domain shifts across imaging modalities, such as CT and MRI. Although recent vision-language representation learning methods have shown promise in medical image analysis, their role in cross-modality UDA segmentation remains underexplored. To address this problem, we propose TCSA-UDA, a Text-driven Cross-Semantic Alignment framework that uses modality-aware textual prompting to guide domain-invariant visual representation learning. Specifically, we introduce a vision-language covariance cosine loss (VLCoL) that aligns inter-class visual feature relationships with text-derived semantic relationships, encouraging the image encoder to learn semantically structured and modality-robust representations. In addition, we incorporate a prototype alignment module to reduce residual class-level discrepancies between source and target domains by aligning high-level class prototypes. Extensive experiments on cross-modality cardiac, abdominal, and brain tumor segmentation benchmarks demonstrate that TCSA-UDA consistently improves adaptation performance and outperforms state-of-the-art UDA methods. These results highlight the potential of language-driven semantic guidance for domain-adaptive medical image segmentation. The code is available at https://github.com/lalitmaurya47/TCSA_UDA
Read the full abstract

Computer Vision · Cross-listed from cs.LG

MARAuder's Map: Motion-Aware Real-time Activity Recognition with Layout-Based Trajectories

Ambient sensor-based human activity recognition (HAR) in smart homes remains challenging due to the need for real-time inference, spatially grounded reasoning, and context-aware temporal modeling. Existing approaches often rely on pre-segmented, within-activity data and overlook the physical layout of the environment, limiting their robustness in continuous, real-world deployments. In this paper, we propose MARAuder's Map, a novel framework for real-time activity recognition from raw, unsegmented sensor streams. Our method projects sensor activations onto the physical floorplan to generate trajectory-aware, image-like sequences that capture the spatial flow of human movement. These representations are processed by a hybrid deep learning model that jointly captures spatial structure and temporal dependencies. To enhance temporal awareness, we introduce a learnable time embedding module that encodes contextual cues such as hour-of-day and day-of-week. Additionally, an attention-based encoder selectively focuses on informative segments within each observation window, enabling accurate recognition even under cross-activity transitions and temporal ambiguity. Extensive experiments on multiple real-world smart home datasets demonstrate that our method outperforms strong baselines, offering a practical solution for real-time HAR in ambient sensor environments.
Read the full abstract

All authors Zishuai Liu, Weihang You, Jin Lu, Fei Dou

Computer Vision

Sign language recognition from skeletal data using graph and recurrent neural networks

This work presents an approach for recognizing isolated sign language gestures using skeleton-based pose data extracted from video sequences. A Graph-GRU temporal network is proposed to model both spatial and temporal dependencies between frames, enabling accurate classification. The model is trained and evaluated on the AUTSL (Ankara university Turkish sign language) dataset, achieving high accuracy. Experimental results demonstrate the effectiveness of integrating graph-based spatial representations with temporal modeling, providing a scalable framework for sign language recognition. The results of this approach highlight the potential of pose-driven methods for sign language understanding.
Read the full abstract

All authors B. Mederos, J. Mejía, A. Medina-Reyes, Y. Espinosa-Almeyda, J. D. Díaz-Roman, I. Rodríguez-Mederos, M. Mejía-Carreon, F. Gonzalez-Lopez

Friday 7 November

Computer Vision

A Second-Order Attention Mechanism For Prostate Cancer Segmentation and Detection in Bi-Parametric MRI

The detection of clinically significant prostate cancer lesions (csPCa) from biparametric magnetic resonance imaging (bp-MRI) has emerged as a noninvasive imaging technique for improving accurate diagnosis. Nevertheless, the analysis of such images remains highly dependent on the subjective expert interpretation. Deep learning approaches have been proposed for csPCa lesions detection and segmentation, but they remain limited due to their reliance on extensively annotated datasets. Moreover, the high lesion variability across prostate zones poses additional challenges, even for expert radiologists. This work introduces a second-order geometric attention (SOGA) mechanism that guides a dedicated segmentation network, through skip connections, to detect csPCa lesions. The proposed attention is modeled on the Riemannian manifold, learning from symmetric positive definitive (SPD) representations. The proposed mechanism was integrated into standard U-Net and nnU-Net backbones, and was validated on the publicly available PI-CAI dataset, achieving an Average Precision (AP) of 0.37 and an Area Under the ROC Curve (AUC-ROC) of 0.83, outperforming baseline networks and attention-based methods. Furthermore, the approach was evaluated on the Prostate158 dataset as an independent test cohort, achieving an AP of 0.37 and an AUC-ROC of 0.75, confirming robust generalization and suggesting discriminative learned representations.
Read the full abstract

Computer Vision

Towards Better Ultrasound Video Segmentation Foundation Model: An Empirical study on SAM2 Finetuning from Data Perspective

Ultrasound (US) video segmentation remains a challenging problem due to strong inter- and intra-dataset variability, motion artifacts, and limited annotated data. Although foundation models such as Segment Anything Model 2 (SAM2) demonstrate strong zero-shot and prompt-guided segmentation capabilities, their performance deteriorates substantially when transferred to medical imaging domains. Current adaptation studies mainly emphasize architectural modifications, while the influence of data characteristics and training regimes has not been systematically examined. In this study, we present a comprehensive, data-centric investigation of SAM2 adaptation for ultrasound video segmentation. We analyze how training-set size, video duration, and augmentation schemes affect adaptation performance under three paradigms: task-specific fine-tuning, intermediate adaptation, and multi-task joint training, across five SAM2 variants and multiple prompting modes. We further design six ultrasound-specific augmentations, assessing their effect relative to generic strategies. Experiments on three representative ultrasound datasets reveal that data scale and temporal context play a more decisive role than model architecture or initialization. Moreover, joint training offers an efficient compromise between modality alignment and task specialization. This work aims to provide empirical insights for developing efficient, data-aware adaptation pipelines for SAM2 in ultrasound video analysis.
Read the full abstract

All authors Xing Yao, Ahana Gangopadhyay, Hsi-Ming Chang, Ravi Soni

Computer Vision

Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels of complexity, and the resulting dataset with over 1M high-quality problems including: reasoning traces, preference data, and instruction prompts supporting SFT, offline and online RL. Our vision-centric synthesis framework uses a two-stage process focusing on: (1) generating diverse verifiable questions from existing images at scale, and (2) creating complex compositional visual problems by merging simpler questions. Remarkably, finetuning Qwen2.5-VL-7B on our data outperforms existing open-data baselines across evaluated vision-centric benchmarks, and our best configurations match or surpass strong closed-data models such as MiMo-VL-7B-RL on Vstar Bench, CV-Bench and MMStar-V. Notably, despite being entirely vision-centric, our data transfers positively to text-only reasoning (MMLU-Pro, +3.7%) and audio reasoning (MMAU, +1.32%), demonstrating its effectiveness. Similarly, despite containing no embodied visual data, we observe notable gains (NiEH, +8.8%) when evaluating open-ended embodied QA. Lastly, we use our data to comprehensively analyze at scale (1M+) the entire VLM post-training pipeline showing that (i) SFT on high-quality data with cognitive behaviors on reasoning traces is essential to scale online RL, (ii) offline RL could match online RL's performance while disaggregating compute demands, and, (iii) SFT on high quality data also improve out-of-domain, cross-modality transfer.
Read the full abstract

All authors David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung, Ximing Lu, Prithviraj Ammanabrolu, Hyunwoo Kim, Yuan-Hong Liao, Yejin Choi

Computer Vision

Pedicle Screw Pairing and Registration for Screw Pose Estimation from Dual C-arm Images Using CAD Models

Accurate matching of pedicle screws in both anteroposterior (AP) and lateral (LAT) images is critical for successful spinal decompression and stabilization during surgery. However, establishing screw correspondence, especially in LAT views, remains a significant clinical challenge. This paper introduces a method to address pedicle screw correspondence and pose estimation from dual C-arm images. By comparing screw combinations, the approach demonstrates consistent accuracy in both pairing and registration tasks. The method also employs 2D-3D alignment with screw CAD 3D models to accurately pair and estimate screw pose from dual views. Our results show that the correct screw combination consistently outperforms incorrect pairings across all test cases, even prior to registration. After registration, the correct combination further enhances alignment between projections and images, significantly reducing projection error. This approach shows promise for improving surgical outcomes in spinal procedures by providing reliable feedback on screw positioning.
Read the full abstract

All authors Yehyun Suh, Lin Li, Aric Plumley, Chaochao Zhou, Daniel Moyer, Kongbin Kang

Computer Vision

VMDT: Decoding the Trustworthiness of Video Foundation Models

As foundation models become more sophisticated, ensuring their trustworthiness becomes increasingly critical; yet, unlike text and image, the video modality still lacks comprehensive trustworthiness benchmarks. We introduce VMDT (Video-Modal DecodingTrust), the first unified platform for evaluating text-to-video (T2V) and video-to-text (V2T) models across five key trustworthiness dimensions: safety, hallucination, fairness, privacy, and adversarial robustness. Through our extensive evaluation of 7 T2V models and 19 V2T models using VMDT, we uncover several significant insights. For instance, all open-source T2V models evaluated fail to recognize harmful queries and often generate harmful videos, while exhibiting higher levels of unfairness compared to image modality models. In V2T models, unfairness and privacy risks rise with scale, whereas hallucination and adversarial robustness improve – though overall performance remains low. Uniquely, safety shows no correlation with model size, implying that factors other than scale govern current safety levels. Our findings highlight the urgent need for developing more robust and trustworthy video foundation models, and VMDT provides a systematic framework for measuring and tracking progress toward this goal. The code is available at https://sunblaze-ucb.github.io/VMDT-page/.
Read the full abstract

All authors Yujin Potter, Zhun Wang, Nicholas Crispino, Kyle Montgomery, Alexander Xiong, Ethan Y. Chang, Francesco Pinto, Yuqi Chen, Rahul Gupta, Morteza Ziyadi, Christos Christodoulopoulos, Bo Li, Chenguang Wang, Dawn Song

Computer Vision

Culture in Action: Evaluating Text-to-Image Models through Social Activities

Text-to-image (T2I) diffusion models achieve impressive photorealism by training on large-scale web data, but models inherit cultural biases and fail to depict underrepresented regions faithfully. Existing cultural benchmarks focus mainly on object-centric categories (e.g., food, attire, and architecture), overlooking the social and daily activities that more clearly reflect cultural norms. Few metrics exist for measuring cultural faithfulness. We introduce CULTIVate, a benchmark for evaluating T2I models on cross-cultural activities (e.g., greetings, dining, games, traditional dances, and cultural celebrations). CULTIVate spans 16 countries with 576 prompts and more than 19,000 images, and provides an explainable descriptor-based evaluation framework across multiple cultural dimensions, including background, attire, objects, and interactions. We propose four metrics to measure cultural alignment, hallucination, exaggerated elements, and diversity. Our findings reveal systematic disparities: models perform better for global north countries than for the global south, with distinct failure modes across T2I systems. Human studies confirm that our metrics correlate more strongly with human judgments than existing text-image metrics.
Read the full abstract

Computer Vision · Cross-listed from cs.RO

Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots

The deployment of artificial intelligence models at the edge is increasingly critical for autonomous robots operating in GPS-denied environments where local, resource-efficient reasoning is essential. This work demonstrates the feasibility of deploying small Vision-Language Models (VLMs) on mobile robots to achieve real-time scene understanding and reasoning under strict computational constraints. Unlike prior approaches that separate perception from mobility, the proposed framework enables simultaneous movement and reasoning in dynamic environments using only on-board hardware. The system integrates a compact VLM with multimodal perception to perform contextual interpretation directly on embedded hardware, eliminating reliance on cloud connectivity. Experimental validation highlights the balance between computational efficiency, task accuracy, and system responsiveness. Implementation on a mobile robot confirms one of the first successful deployments of small VLMs for concurrent reasoning and mobility at the edge. This work establishes a foundation for scalable, assured autonomy in applications such as service robotics, disaster response, and defense operations.
Read the full abstract

All authors Justin Williams, Kishor Datta Gupta, Roy George, Mrinmoy Sarkar

Computer Vision

Visual Spatial Tuning

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders, which brings extra overhead and usually harms general capabilities. To enhance the spatial ability in general architectures, we introduce Visual Spatial Tuning (VST), a comprehensive framework to cultivate VLMs with human-like visuospatial abilities, from spatial perception to reasoning. We first attempt to enhance spatial perception in VLMs by constructing a large-scale dataset termed VST-P, which comprises 4.1 million samples spanning 19 skills across single views, multiple images, and videos. Then, we present VST-R, a curated dataset with 135K samples that instruct models to reason in space. In particular, we adopt a progressive training pipeline: supervised fine-tuning to build foundational spatial knowledge, followed by reinforcement learning to further improve spatial reasoning abilities. Without the side-effect to general capabilities, the proposed VST consistently achieves state-of-the-art results on several spatial benchmarks, including $34.8\%$ on MMSI-Bench and $61.2\%$ on VSIBench. It turns out that the Vision-Language-Action models can be significantly enhanced with the proposed spatial tuning paradigm, paving the way for more physically grounded AI.
Read the full abstract

All authors Rui Yang, Ziyu Zhu, Yanwei Li, Jingjia Huang, Shen Yan, Siyuan Zhou, Zhe Liu, Xiangtai Li, Shuangye Li, Wenqian Wang, Yi Lin, Hengshuang Zhao

Computer Vision

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning

Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Existing works attempt to progressively narrow the search space. However, these approaches typically rely on a hand-crafted search process, lacking end-to-end optimization for learning optimal search strategies. In this paper, we propose TimeSearch-R, which reformulates temporal search as interleaved text-video thinking, seamlessly integrating searching video clips into the reasoning process through reinforcement learning (RL). However, applying RL training methods, such as Group Relative Policy Optimization (GRPO), to video reasoning can result in unsupervised intermediate search decisions. This leads to insufficient exploration of the video content and inconsistent logical reasoning. To address these issues, we introduce GRPO with Completeness Self-Verification (GRPO-CSV), which gathers searched video frames from the interleaved reasoning process and utilizes the same policy model to verify the adequacy of searched frames, thereby improving the completeness of video reasoning. Additionally, we construct datasets specifically designed for the SFT cold-start and RL training of GRPO-CSV, filtering out samples with weak temporal dependencies to enhance task difficulty and improve temporal search capabilities. Extensive experiments demonstrate that TimeSearch-R achieves significant improvements on temporal search benchmarks such as Haystack-LVBench and Haystack-Ego4D, as well as long-form video understanding benchmarks like VideoMME and MLVU. Notably, TimeSearch-R establishes a new state-of-the-art on LongVideoBench with 4.1% improvement over the base model Qwen2.5-VL and 2.0% over the advanced video reasoning model Video-R1. Our code is available at https://github.com/Time-Search/TimeSearch-R.
Read the full abstract

All authors Junwen Pan, Qizhe Zhang, Rui Zhang, Ming Lu, Xin Wan, Yuan Zhang, Chang Liu, Qi She

Computer Vision · Cross-listed from cs.LG

On Flow Matching KL Divergence

We derive a deterministic, non-asymptotic upper bound on the Kullback-Leibler (KL) divergence of the flow-matching distribution approximation. In particular, if the $L_2$ flow-matching loss is bounded by $\epsilon^2 > 0$, then the KL divergence between the true data distribution and the estimated distribution is bounded by $A_1 \epsilon + A_2 \epsilon^2$. Here, the constants $A_1$ and $A_2$ depend only on the regularities of the data and velocity fields. Consequently, this bound implies statistical convergence rates of Flow Matching Transformers under the Total Variation (TV) distance. We show that, flow matching achieves nearly minimax-optimal efficiency in estimating smooth distributions. Our results make the statistical efficiency of flow matching comparable to that of diffusion models under the TV distance. Numerical studies on synthetic and learned velocities corroborate our theory.
Read the full abstract

All authors Maojiang Su, Jerry Yao-Chieh Hu, Sophia Pi, Han Liu

Computer Vision

GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling

Medical image segmentation demands models that achieve high accuracy while maintaining computational efficiency and clinical interpretability. While recent Kolmogorov-Arnold Networks (KANs) offer powerful adaptive non-linearities, their full-channel spline transformations incur a quadratic parameter growth of $\mathcal{O}(C^{2}(G+k))$ with respect to the channel dimension $C$, where $G$ and $k$ denote the number of grid intervals and spline polynomial order, respectively. Moreover, unconstrained spline mappings lack structural constraints, leading to excessive functional freedom, which may cause overfitting under limited medical annotations. To address these challenges, we propose GroupKAN (Grouped Kolmogorov-Arnold Networks), an efficient architecture driven by group-structured spline modeling. Specifically, we introduce: (1) Grouped KAN Transform (GKT), which restricts spline interactions to intra-group channel mappings across $g$ groups, effectively reducing the spline-induced quadratic expansion to \textbf{$\mathcal{O}(C^2(\frac{G+k}{g} + 1))$}, thereby significantly lowering the effective quadratic coefficient; and (2) Grouped KAN Activation (GKA), which applies shared spline functions within each group to enable efficient token-wise non-linearities. By imposing structured constraints on channel interactions, GroupKAN achieves a substantial reduction in parameter redundancy without sacrificing expressive capacity.Extensive evaluations on three medical benchmarks (BUSI, GlaS, and CVC) demonstrate that GroupKAN achieves an average IoU of 79.80%, outperforming the strong U-KAN baseline by +1.11% while requiring only 47.6% of the parameters (3.02M vs. 6.35M). Qualitative results further reveal that GroupKAN produces sharply localized activation maps that better align with the ground truth than MLPs and KANs, significantly enhancing clinical interpretability.
Read the full abstract

All authors Guojie Li, Tianyi Liu, Anwar P.P. Abdul Majeed, Muhammad Ateeq, Anh Nguyen, Fan Zhang

Computer Vision

Semantic-Guided Natural Language and Visual Fusion for Cross-Modal Interaction Based on Tiny Object Detection

This paper introduces a cutting-edge approach to cross-modal interaction for tiny object detection by combining semantic-guided natural language processing with advanced visual recognition backbones. The proposed method integrates the BERT language model with the CNN-based Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN-Net), incorporating innovative backbone architectures such as ELAN, MSP, and CSP to optimize feature extraction and fusion. By employing lemmatization and fine-tuning techniques, the system aligns semantic cues from textual inputs with visual features, enhancing detection precision for small and complex objects. Experimental validation using the COCO and Objects365 datasets demonstrates that the model achieves superior performance. On the COCO2017 validation set, it attains a 52.6% average precision (AP), outperforming YOLO-World significantly while maintaining half the parameter consumption of Transformer-based models like GLIP. Several test on different of backbones such ELAN, MSP, and CSP further enable efficient handling of multi-scale objects, ensuring scalability and robustness in resource-constrained environments. This study underscores the potential of integrating natural language understanding with advanced backbone architectures, setting new benchmarks in object detection accuracy, efficiency, and adaptability to real-world challenges.
Read the full abstract

All authors Xian-Hong Huang, Hui-Kai Su, Chi-Chia Sun, Jun-Wei Hsieh

Computer Vision

EventFlow: Real-Time Neuromorphic Event-Driven Classification of Two-Phase Boiling Flow Regimes

Flow boiling is an efficient heat transfer mechanism capable of dissipating high heat loads with minimal temperature variation, making it an ideal thermal management method. However, sudden shifts between flow regimes can disrupt thermal performance and system reliability, highlighting the need for accurate and low-latency real-time monitoring. Conventional optical imaging methods are limited by high computational demands and insufficient temporal resolution, making them inadequate for capturing transient flow behavior. To address this, we propose a real-time framework based on signals from neuromorphic sensors for flow regime classification. Neuromorphic sensors detect changes in brightness at individual pixels, which typically correspond to motion at edges, enabling fast and efficient detection without full-frame reconstruction, providing event-based information. We develop five classification models using both traditional image data and event-based data, demonstrating that models leveraging event data outperform frame-based approaches due to their sensitivity to dynamic flow features. Among these models, the event-based long short-term memory model provides the best balance between accuracy and speed, achieving 97.6% classification accuracy with a processing time of 0.28 ms. Our asynchronous processing pipeline supports continuous, low-latency predictions and delivers stable output through a majority voting mechanisms, enabling reliable real-time feedback for experimental control and intelligent thermal management.
Read the full abstract

All authors Sanghyeon Chang, Srikar Arani, Nishant Sai Nuthalapati, Youngjoon Suh, Nicholas Choi, Siavash Khodakarami, Md Rakibul Hasan Roni, Nenad Miljkovic, Aparna Chandramowlishwaran, Yoonjin Won

Computer Vision

Photo Dating by Facial Age Aggregation

We introduce a novel method for Photo Dating which estimates the year a photograph was taken by leveraging information from the faces of people present in the image. To facilitate this research, we publicly release CSFD-1.6M, a new dataset containing over 1.6 million annotated faces, primarily from movie stills, with identity and birth year annotations. Uniquely, our dataset provides annotations for multiple individuals within a single image, enabling the study of multi-face information aggregation. We propose a probabilistic framework that formally combines visual evidence from modern face recognition and age estimation models, and career-based temporal priors to infer the photo capture year. Our experiments demonstrate that aggregating evidence from multiple faces consistently improves the performance and the approach significantly outperforms strong, scene-based baselines, particularly for images containing several identifiable individuals.
Read the full abstract

Computer Vision · Cross-listed from cs.LG

SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning

Recent studies have demonstrated the effectiveness of clustering-based approaches for self-supervised and unsupervised learning. However, the application of clustering is often heuristic, and the optimal methodology remains unclear. In this work, we establish connections between these unsupervised clustering methods and classical mixture models from statistics. Through this framework, we demonstrate significant enhancements to these clustering methods, leading to the development of a novel model named SiamMM. Our method attains state-of-the-art performance across various self-supervised learning benchmarks. Inspection of the learned clusters reveals a strong resemblance to unseen ground truth labels, uncovering potential instances of mislabeling.
Read the full abstract

Computer Vision

The Potential of Copernicus Satellites for Disaster Response: Retrieving Building Damage from Sentinel-1 and Sentinel-2

Natural disasters demand rapid damage assessment to guide humanitarian response. Here, we investigate whether medium-resolution Earth observation images from the Copernicus program can support building damage assessment, complementing very-high resolution imagery with often limited availability. We introduce xBD-S12, a dataset of 10,315 pre- and post-disaster image pairs from both Sentinel-1 and Sentinel-2, spatially and temporally aligned with the established xBD benchmark. In a series of experiments, we demonstrate that building damage can be detected and mapped rather well in many disaster scenarios, despite the moderate 10$\,$m ground sampling distance. We also find that, for damage mapping at that resolution, architectural sophistication does not seem to bring much advantage: more complex model architectures tend to struggle with generalization to unseen disasters, and geospatial foundation models bring little practical benefit. Our results suggest that Copernicus images are a viable data source for rapid, wide-area damage assessment and could play an important role alongside VHR imagery. We release the xBD-S12 dataset, code, and trained models to support further research at https://github.com/prs-eth/xbd-s12 .
Read the full abstract

All authors Olivier Dietrich, Merlin Alfredsson, Emilia Arens, Nando Metzger, Torben Peters, Linus Scheibenreif, Jan Dirk Wegner, Konrad Schindler

Computer Vision

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

Recent advances in 3D point cloud transformers have led to state-of-the-art results in tasks such as semantic segmentation and reconstruction. However, these models typically rely on dense token representations, incurring high computational and memory costs during training and inference. In this work, we present the finding that tokens are remarkably redundant, leading to substantial inefficiency. We introduce gitmerge3D, a globally informed graph token merging method that can reduce the token count by up to 90-95% while maintaining competitive performance. This finding challenges the prevailing assumption that more tokens inherently yield better performance and highlights that many current models are over-tokenized and under-optimized for scalability. We validate our method across multiple 3D vision tasks and show consistent improvements in computational efficiency. This work is the first to assess redundancy in large-scale 3D transformer models, providing insights into the development of more efficient 3D foundation architectures. Our code and checkpoints are publicly available at https://gitmerge3d.github.io
Read the full abstract

All authors Tuan Anh Tran, Duy M. H. Nguyen, Hoai-Chau Tran, Michael Barz, Khoa D. Doan, Roger Wattenhofer, Ngo Anh Vien, Mathias Niepert, Daniel Sonntag, Paul Swoboda

Computer Vision

Shared Latent Representation for Joint Text-to-Audio-Visual Synthesis

We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face generation. To handle distribution shifts between clean and TTS-predicted features, we adopt a two-stage training: pretraining on Wav2Vec2 embeddings and finetuning on TTS outputs. This enables tight audio-visual alignment, preserves speaker identity, and produces natural, expressive speech and synchronized facial motion without ground-truth audio at inference. Experiments show that conditioning on TTS-predicted latent features outperforms cascaded pipelines, improving both lip-sync and visual realism.
Read the full abstract

All authors Dogucan Yaman, Seymanur Akti, Fevziye Irem Eyiokur, Alexander Waibel

Computer Vision

Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration

Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few works have been attempted in the direction of image restoration. Handling large image sizes and the divergent nature of various degradation poses a unique challenge in the restoration domain. However, existing works require heavily engineered architectural modifications for new task adaptation, resulting in significant computational overhead. Regularization-based methods are unsuitable for restoration, as different restoration challenges require different kinds of feature processing. In this direction, we propose a simple modification of the convolution layer to adapt the knowledge from previous restoration tasks without touching the main backbone architecture. Therefore, it can be seamlessly applied to any deep architecture without any structural modifications. Unlike other approaches, we demonstrate that our model can increase the number of trainable parameters without significantly increasing computational overhead or inference time. Experimental validation demonstrates that new restoration tasks can be introduced without compromising the performance of existing tasks. We also show that performance on new restoration tasks improves by adapting the knowledge from the knowledge base created by previous restoration tasks. The code is available at https://github.com/aupendu/continual-restore.
Read the full abstract

Computer Vision

Multi-modal Loop Closure Detection with Foundation Models in Severely Unstructured Environments

Robust loop closure detection is a critical component of Simultaneous Localization and Mapping (SLAM) algorithms in GNSS-denied environments, such as in the context of planetary exploration. In these settings, visual place recognition often fails due to aliasing and weak textures, while LiDAR-based methods suffer from sparsity and ambiguity. This paper presents MPRF, a multimodal pipeline that leverages transformer-based foundation models for both vision and LiDAR modalities to achieve robust loop closure in severely unstructured environments. Unlike prior work limited to retrieval, MPRF integrates a two-stage visual retrieval strategy with explicit 6-DoF pose estimation, combining DINOv2 features with SALAD aggregation for efficient candidate screening and SONATA-based LiDAR descriptors for geometric verification. Experiments on the S3LI dataset and S3LI Vulcano dataset show that MPRF outperforms state-of-the-art retrieval methods in precision while enhancing pose estimation robustness in low-texture regions. By providing interpretable correspondences suitable for SLAM back-ends, MPRF achieves a favorable trade-off between accuracy, efficiency, and reliability, demonstrating the potential of foundation models to unify place recognition and pose estimation. Code and models will be released at github.com/DLR-RM/MPRF.
Read the full abstract

All authors Laura Alejandra Encinar Gonzalez, John Folkesson, Rudolph Triebel, Riccardo Giubilato