Human Pose and Action Recognition

Derniers papiers

• Hands-On: Segmenting Individual Signs from Continuous Sequences

  JianHe Low, Harry Walsh, Ozge Mercanoglu Sincan, Richard Bowden · 27 mai 2026

  This work tackles the challenge of continuous sign language segmentation, a key task with huge implications for sign language translation and data annotation. We propose a transformer-based architecture that models the temporal dynamics of signing and frames segmentation as a sequence labeling probl…

• Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective

  Xiang Fang, Zeyu Xiong, Wanlong Fang, Xiaoye Qu, Chen Chen, Jianfeng Dong, Keke Tang, Pan Zhou, Yu Cheng, Daizong Liu · 27 mai 2026

  This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have …

• MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images

  Yunqi Gao, Leyuan Liu, Yuhan Li, Changxin Gao, Jingying Chen · 26 mai 2026

  3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation, we propose to address these two tasks within a unified framework, which allows …

• DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition

  Jingmin Zhu, Anqi Zhu, James Bailey, Jun Liu, Hossein Rahmani, Mohammed Bennamoun, Farid Boussaid, Qiuhong Ke · 26 mai 2026

  Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantics. This coarse-grained alignment fails to bridge the domain shift between seen and unseen classes, thereby impeding the …

• AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

  Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim · 26 mai 2026

  As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highly dependent on the sensing setup, including body location, mounting position, sensor orientation, device hardware, and s…

• Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode Modeling

  Zikang Zhou, Haibo Hu, Xinhong Chen, Yifan Zhang, Nan Guan, Yung-Hui Li, Chun Jason Xue, Jianping Wang · 26 mai 2026

  Multimodal motion forecasting is inherently under-supervised: each training scene provides only one realized future, yet multiple plausible futures exist. This sparse supervision often leads to mode collapse (redundant hypotheses and insufficient mode coverage) and unreliable confidence ranking when…

• Hadamard Representation: Scaffolding Performance Across Model-free RL

  Jacob E. Kooi, Zhao Yang, Mark Hoogendoorn, Vincent Fran\c{c}ois-Lavet · 26 mai 2026

  Deep reinforcement learning agents progressively lose representational capacity during training: neurons become dormant, removing active capacity from the network, and effective rank collapses, leaving surviving neurons redundant. Existing remedies such as periodic resets, and special neural network…

• Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization

  Tianyu Wang (School of Economics and Management, Beihang University, Beijing 100191, China), Junjie Wu (School of Economics and Management, Beihang University, Beijing 100191, China, Key Laboratory of Data Intelligence and Management, Beihang University, Ministry of Industry and Information Technology, Beijing 100191, China), Jingquan Gao (School of Economics and Management, Beihang University, Beijing 100191, China), Shishuo Li (School of Economics and Management, Beihang University, Beijing 100191, China) · 25 mai 2026

  Temporal Action Localization (TAL) has been extensively studied in generic video understanding, while fine-grained sports scenarios, such as professional badminton, remain underexplored due to their complex and subtle spatio-temporal dynamics. In this paper, we focus on fine-grained TAL in professio…

• VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026

  Qiaohui Chu, Haoyu Zhang, Yisen Feng, Meng Liu, Weili Guan, Dongmei Jiang, Liqiang Nie · 22 mai 2026

  We propose VISTA, a V-JEPA Integrated StillFast Temporal Anticipator for the Ego4D Short-Term Object Interaction Anticipation (STA) Challenge at EgoVis 2026. Given an egocentric video timestamp, the task requires anticipating the next human-object interaction, including the future active object's bo…

• Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition

  Mengyuan Liu, Ziyi Wang, Peiming Li, Junsong Yuan · 20 mai 2026

  RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing methods rely on post-capture algorithms, which fail to protect privacy during data acquisition. We propose Lens Privacy Sealing (LPS), a simple hardwar…

• Visual Timelines of Police Encounters in Body-Worn Camera Footage: Operational Context and Activity Cataloging for Training and Analysis in OpenBWC

  Angela Srbinovska, Christopher Homan, Adrian Martin, Ernest Fokou\'e · 19 mai 2026

  Law enforcement agencies are accumulating vast amounts of body-worn camera (BWC) footage. However, this remains operationally opaque. That is, analysts and trainers still have to invest considerable time watching full-length videos to pinpoint the start of key encounters and identify the points wher…

• HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation

  Vinduja Thekkath, Ashish Musale, Ajay Waghumbare, Upasna Singh · 18 mai 2026

  We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human skeleton. Current state-of-the-art pose estimators aim to c…

• FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy

  Qian He, Zhenshuo Yang, Wenqi Liang, Chunhui Hao, Nicu Sebe, Jiandong Tian · 18 mai 2026

  Visuomotor policies aim to learn complex manipulation tasks from expert demonstrations. However, generating smooth and coherent trajectories remains challenging, as it requires balancing proximal precision with distal foresight. Existing approaches typically focus on optimizing intra-chunk action di…

• Latent Video Prediction Learns Better World Models

  Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam, James Bailey, Naveed Akhtar · 18 mai 2026

  Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score on clean benchmarks. This leaves a major gap in comprehending their potential as world models. We present the first systematic study addressing this ga…

• BioHuman: Learning Biomechanical Human Representations from Video

  Yujun Huo, He Zhang, Chentao Song, Honglin Song, Zongyu Zuo, Tao Yu · 15 mai 2026

  Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the lack of large-scale datasets with biomechanical annotations, and by existing approaches that cannot directly infer inter…

• STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition

  Hongli Liu, Yu Wang, Shengjie Zhao · 14 mai 2026

  Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal misalignment, where static textual prompts fail to capture decis…

• Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers

  Sahil Bhandary Karnoor, Romit Roy Choudhury · 13 mai 2026

  Pose estimation refers to tracking a human's full body posture, including their head, torso, arms, and legs. The problem is challenging in practical settings where the number of body sensors are limited. Past work has shown promising results using conditional diffusion models, where the pose predict…

• LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute

  Ali Salamatian, Anthony Fuller, Pritam Sarkar, James R. Green, Leonid Sigal, Evan Shelhamer · 11 mai 2026

  Transformers dominate video recognition. They split videos into tokens, and processing them has expensive superlinear computational cost. Yet videos are filled with redundancy, so we can question the need for this expense. We introduce LookWhen, a selector-extractor framework that factorizes video r…

• Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition

  Talha Ilyas, Deval Mehta, Zongyuan Ge · 11 mai 2026

  Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to interpret. In this work, we introduce a neurosymbolic formulation of skeleton-based HAR that reframes action recognition as concept-driven first-order log…

• Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts

  Wenhan Zheng, Yuyi Mao, Ivan Wang-Hei Ho · 8 mai 2026

  Channel state information (CSI)-based human activity recognition (HAR) is vulnerable to performance degradation under domain shifts across varying physical environments. Continual learning (CL) offers a principled way to learn new domains sequentially while preserving past knowledge, but existing CL…

• IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction

  Haoshen Zhang, Di Wen, Kunyu Peng, David Schneider, Zeyun Zhong, Alexander Jaus, Zdravko Marinov, Jiale Wei, Ruiping Liu, Junwei Zheng, Yufan Chen, Yufeng Zhang, Yuanhao Luo, Lei Qi, Rainer Stiefelhagen · 6 mai 2026

  We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivated by the need for high-quality structured supervision for learning robot manipulation from human demonstration. IMPACT-H…

• Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence

  Zhiyuan Li, Rongzhen Zhao, Wenyan Yang, Wenshuai Zhao, Pekka Marttinen, Joni Pajarinen · 6 mai 2026

  The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive approximations of discrete correspondence problems. Modern self-…

• IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning

  Qian Yin, Di Wen, Kunyu Peng, David Schneider, Zeyun Zhong, Alexander Jaus, Zdravko Marinov, Jiale Wei, Ruiping Liu, Junwei Zheng, Yufan Chen, Chen Zhang, Lei Qi, Rainer Stiefelhagen · 6 mai 2026

  Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limiting reuse of information on annotator uncertainty and model reliability. We intr…

• BadmintonGRF: A Multimodal Dataset and Benchmark for Markerless Ground Reaction Force Estimation in Badminton

  Kuoye Niu, Jianwei Li, Shengze Cai, Yong Ma, Mengyao Jia, Lishun Shen, Zhenheng Zhang, Yuxin Peng, Xian Song · 6 mai 2026

  Multimodal resources for non-periodic court sports with laboratory-grade sensing remain scarce: few publicly pair instrumented ground reaction force (GRF) with high-frame-rate multi-view video, limiting markerless load estimation in realistic training settings. BadmintonGRF records eight synchronize…

• VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition

  Tanush Yadav, Mohammadreza Salehi, Jae Sung Park, Vivek Ramanujan, Hannaneh Hajishirzi, Yejin Choi, Ali Farhadi, Rohun Tripathi, Ranjay Krishna · 5 mai 2026

  Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understanding. Unfortunately, due to a lack of sufficiently diverse and challenging data, modern vision-language models (VLMs) a…