Human Pose and Action Recognition

Derniers papiers

• SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation

  Edoardo Bianchi, Antonio Liotta · 17 juin 2026

  Estimating human proficiency from video is a key challenge for automated skill assessment, with applications in sports coaching, music pedagogy, surgical training, and workplace learning. Existing approaches often focus on individual scenarios or rely on shared multi-view aggregation, limiting their…

• Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition

  Alessandro Sottovia, Alessandro Torcinovich, Oswald Lanz · 17 juin 2026

  Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent frame…

• MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition

  Hyejeong Im, Wonseon Lim, Dae-Won Kim · 16 juin 2026

  Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environments requires detecting novel activities while continuously learning from non-stationary data streams. Existing methods…

• Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning

  Qinwu Xu · 16 juin 2026

  Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning. Reconstruction-based approaches such as MAE and VideoMAE learn representations by recovering masked visual content \cite{he2022mae,tong2022…

• A Machine Learning Framework for Real-Time Personalized Ergonomic Pose Analysis

  Manex Atxa, Bruno Simoes, Julen Balzategui · 12 juin 2026

  This paper introduces a new methodology for real-time prediction of ergonomic and non-ergonomic human poses using volumetric video data in three dimensions. Although the methodology was designed for ergonomic assessments, it can be adapted to other applications requiring real-time analysis of human …

• EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence

  Xin Zhou, Cong Miao · 12 juin 2026

  In this paper, we propose the Enhanced World Action Model (EWAM), a closed-loop online adaptation architecture built upon a pretrained and fully frozen Cosmos3 backbone network. Evaluated entirely under a zero-shot task protocol, EWAM is centrally focused on reducing the amount of additional deploym…

• ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

  Hosu Lee, Junho Kim, Hyunjun Kim, Yong Man Ro · 12 juin 2026

  Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs. Prior works attempted to solve this wi…

• Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding

  Tarandeep Singh, Soumyanetra Pal, Soham Biswas, Nishanth Chandran · 11 juin 2026

  In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural language. We propose a three-stage pipeline that decomposes the accident unders…

• Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization

  Parth Agrawal, Ronit, Sagar Kumar, Aashish Bhambri · 10 juin 2026

  Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches and their limitations in sports analysis for individuals, alongside developing a practical lightweight prototype for real world testing and usage. The …

• Echo-Memory: A Controlled Study of Memory in Action World Models

  Wayne King, Zeyue Xue, Yuxuan Bian, Jie Huang, Haoran Li, Yaowei Li, Yaofeng Su, Yuming Li, Haoyu Wang, Shiyi Zhang, Songchun Zhang, Yuwei Niu, Sihan Xu, Junhao Zhuang, Haoyang Huang, Nan Duan · 9 juin 2026

  We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos from a first frame, text prompt, and camera-action sequence, but their central failure is often memory rather than local image synthesis: after the …

• AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

  Jisong Cai, Long Ling, Shiwei Chu, Zhongshan Liu, Jiayue Kang, Zhixuan Liang, Wenjie Xu, Yinan Mao, Weinan Zhang, Xiaokang Yang, Ru Ying, Ran Zheng, Yao Mu · 9 juin 2026

  World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical priors into policy learning. However, existing world-action models couple world prediction and action execution at the same temporal resolution, forc…

• C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache

  Weisen Zhao, Lam Nguyen, Zhicong Lu, Yuzhang Shang · 9 juin 2026

  World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them learn from abundant unlabeled video rather than scarce labeled robot demonstrations. This generalization is computationally…

• Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning

  Yuesen Li, Daniel Link · 9 juin 2026

  Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases. Yet in-possession phases are rarely directly observable and are shaped by evolving tactical intentions, rather than spatial patterns alone. This study proposes …

• EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure Estimation

  Yuan Zeng, Zilue Gao, Yujia Shi, Zongqing Lu, Wenming Yang, QingMin Liao · 8 juin 2026

  Estimating hand-surface contact pressure from an egocentric view is crucial for AR/VR devices, robotic imitation, and ergonomic analysis. Existing methods often discretize pressure signal and process frames independently, leading to quantization errors and temporal inconsistencies. We present \emph{…

• From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes

  Xian Gao, Jiacheng Ruan, Jingsheng Gao, Mingye Xie, Zongyun Zhang, Ting Liu, Yuzhuo Fu · 4 juin 2026

  Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement. Existing AI-based models often rely on classroom video footage to identify and analyze student behavior. While these video-based methods can partially capture and analyze student act…

• ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data

  Haoran Yang, Jiacheng Bao, Yucheng Xin, Haoming Song, Yuyang Tian, Bin Zhao, Dong Wang, Xuelong Li · 4 juin 2026

  Achieving versatile and natural whole-body humanoid interaction control remains challenging due to the high cost of whole-body teleoperation data. We present ZeroWBC, a teleoperation-free framework that learns humanoid whole-body interaction from human egocentric videos paired with synchronized whol…

• VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring

  Hanjiang Hu, Yiyuan Pan, Jiaxing Li, Xusheng Luo, Alexander Robey, Na Li, Yebin Wang, Changliu Liu · 3 juin 2026

  As AI systems increasingly assist humans in physical tasks, ensuring safety becomes paramount -- physical actions carry immediate and irreversible consequences that digital errors do not. We introduce the Vision-Language Embodied Safety Agent (VLESA), a framework that monitors human activities from …

• Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

  Zekun Qi, Xuchuan Chen, Dairu Liu, Chenghuai Lin, Yunrui Lian, Sikai Liang, Zhikai Zhang, Yu Guan, Jilong Wang, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi · 3 juin 2026

  We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an agility-generalization trade-off, Humanoid-GPT is pre-trained on a 2B-frame retargeted corpus …

• Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization

  Jingyun Liang, Min Wei, Shikai Li, Yizeng Han, Hangjie Yuan, Lei Sun, Weihua Chen, Fan Wang · 2 juin 2026

  Diffusion models have shown remarkable success in video generation. However, whether such models are truly aware of the 3D structure underlying visual observations, rather than simply reproducing plausible 2D projections, remains an open question. In this work, we investigate this question through h…

• Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection

  Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Qingming Huang · 2 juin 2026

  In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To this end, we propose an Understanding-Enhanced Model Collaboration Method (UE-MCM) that combines efficient coarse-grained video understanding with accurate fine-grained …

• Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models

  Jiacheng Lu, Haoyi Zhu, Sipei Yi, Enze Xie, Yu Li, Cheng Zhuo · 1 juin 2026

  Interactive video world models generate video chunk by chunk in response to user-controlled camera movements, enabling applications such as real-time game simulation, virtual scene navigation, and embodied AI training. However, scaling to long interactive trajectories is prohibitively expensive due …

• ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization

  Kanchan Keisham, Thenukan Pathmanathan, Thangarajah Akilan · 1 juin 2026

  Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches primarily focus on modeling long-range contextual information, often neglecting the critical relative-offset-based local correlations between video fr…

• Joint angle based learning to refine kinematic human pose estimation

  Chang Peng, Yifei Zhou, Haoqiang Ren, Shiqing Huang, Chuangye Chen, Jianming Yang, Bao Yang, Huifeng Xi, Zhenyu Jiang · 1 juin 2026

  Marker-free human pose estimation (HPE) has found increasing applications in various fields. Current HPE suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories when analyzing kinematic human poses. The performance of existing deep learning-based models…

• Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring

  Youhan Huang, Jiajun Li, Yilin Fang, Shuai Wang, Chuheng Li · 29 mai 2026

  Histological scoring is essential for diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD), yet its automation remains challenging due to the high annotation cost and negative transfer among the strongly correlated NAFLD Activity Score (NAS) indicators in multi-task learning. To address this issue, …

• Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification

  Xiao Wang, Minglei Yang, Bin Yang, Wenke Huang, Zheng Wang, Xin Xu, Mang Ye · 28 mai 2026

  Identifying key individuals in video scenes is essential for applications such as automated video editing and intelligent surveillance. Current methods primarily focus on static images and immediate visual cues, overlooking the rich spatio-temporal information in videos. This leads to the phenomenon…