Human Pose and Action Recognition

Últimos artículos

• DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning

  Junho Yoon, Jaemo Jung, Hyunju Kim, Dongman Lee · 24 de diciembre de 2025

  Aligning egocentric video with wearable sensors have shown promise for human action recognition, but face practical limitations in user discomfort, privacy concerns, and scalability. We explore exocentric video with ambient sensors as a non-intrusive, scalable alternative. While prior egocentric-wea…

• How Much 3D Do Video Foundation Models Encode?

  Zixuan Huang, Xiang Li, Zhaoyang Lv, James M. Rehg · 24 de diciembre de 2025

  Videos are continuous 2D projections of 3D worlds. After training on large video data, will global 3D understanding naturally emerge? We study this by quantifying the 3D understanding of existing Video Foundation Models (VidFMs) pretrained on vast video data. We propose the first model-agnostic fram…

• Vidarc: Embodied Video Diffusion Model for Closed-loop Control

  Yao Feng, Chendong Xiang, Xinyi Mao, Hengkai Tan, Zuyue Zhang, Shuhe Huang, Kaiwen Zheng, Haitian Liu, Hang Su, Jun Zhu · 22 de diciembre de 2025

  Robotic arm manipulation in data-scarce settings is a highly challenging task due to the complex embodiment dynamics and diverse contexts. Recent video-based approaches have shown great promise in capturing and transferring the temporal and physical interactions by pre-training on Internet-scale vid…

• Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos

  Mingfei Chen, Yifan Wang, Zhengqin Li, Homanga Bharadhwaj, Yujin Chen, Chuan Qin, Ziyi Kou, Yuan Tian, Eric Whitmire, Rajinder Sodhi, Hrvoje Benko, Eli Shlizerman, Yue Liu · 19 de diciembre de 2025

  Prior works on 3D hand trajectory prediction are constrained by datasets that decouple motion from semantic supervision and by models that weakly link reasoning and action. To address these, we first present the EgoMAN dataset, a large-scale egocentric dataset for interaction stage-aware 3D hand tra…

• KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals

  Shuting Zhao, Zeyu Xiao, Xinrong Chen · 19 de diciembre de 2025

  Full-body motion tracking plays an essential role in AR/VR applications, bridging physical and virtual interactions. However, it is challenging to reconstruct realistic and diverse full-body poses based on sparse signals obtained by head-mounted displays, which are the main devices in AR/VR scenario…

• PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation

  Mengyuan Liu, Jiajie Liu, Jinyan Zhang, Wenhao Li, Junsong Yuan · 19 de diciembre de 2025

  The lifting-based methods have dominated monocular 3D human pose estimation by leveraging detected 2D poses as intermediate representations. The 2D component of the final 3D human pose benefits from the detected 2D poses, whereas its depth counterpart must be estimated from scratch. The lifting-base…

• LAPX: Lightweight Hourglass Network with Global Context

  Haopeng Zhao, Marsha Mariya Kappan, Mahdi Bamdad, Francisco Cruz · 19 de diciembre de 2025

  Human pose estimation is a crucial task in computer vision. Methods that have SOTA (State-of-the-Art) accuracy, often involve a large number of parameters and incur substantial computational cost. Many lightweight variants have been proposed to reduce the model size and computational cost of them. H…

• Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization

  Mengshi Qi, Hongwei Ji, Wulian Yun, Xianlin Zhang, Huadong Ma · 18 de diciembre de 2025

  Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL methods typically focus solely on video-leve…

• SportsGPT: An LLM-driven Framework for Interpretable Sports Motion Assessment and Training Guidance

  Wenbo Tian, Ruting Lin, Hongxian Zheng, Yaodong Yang, Geng Wu, Zihao Zhang, Zhang Zhang · 17 de diciembre de 2025

  Existing intelligent sports analysis systems mainly focus on "scoring and visualization," often lacking automatic performance diagnosis and interpretable training guidance. Recent advances of Large Language Models (LMMs) and motion analysis techniques provide new opportunities to address the above l…

• Supervised Contrastive Frame Aggregation for Video Representation Learning

  Shaif Chowdhury, Mushfika Rahman, Greg Hamerly · 16 de diciembre de 2025

  We propose a supervised contrastive learning framework for video representation learning that leverages temporally global context. We introduce a video to image aggregation strategy that spatially arranges multiple frames from each video into a single input image. This design enables the use of pre …

• PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling

  Haorui Ji, Hongdong Li · 16 de diciembre de 2025

  Diffusion models have demonstrated impressive capabilities in modeling complex data distributions and are increasingly applied in various generative tasks. In this work, we propose Pose Analysis by Diffusion Synthesis PADS, a unified generative modeling framework for 3D human pose analysis. PADS fir…

• 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 · 16 de diciembre de 2025

  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 …

• Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

  Jingmin Zhu, Anqi Zhu, Hossein Rahmani, Jun Liu, Mohammed Bennamoun, Qiuhong Ke · 15 de diciembre de 2025

  We introduce Skeleton-Cache, the first training-free test-time adaptation framework for skeleton-based zero-shot action recognition (SZAR), aimed at improving model generalization to unseen actions during inference. Skeleton-Cache reformulates inference as a lightweight retrieval process over a non-…

• SoccerMaster: A Vision Foundation Model for Soccer Understanding

  Haolin Yang, Jiayuan Rao, Haoning Wu, Weidi Xie · 15 de diciembre de 2025

  Soccer understanding has recently garnered growing research interest due to its domain-specific complexity and unique challenges. Unlike prior works that typically rely on isolated, task-specific expert models, this work aims to propose a unified model to handle diverse soccer visual understanding t…

• Latent Action World Models for Control with Unlabeled Trajectories

  Marvin Alles, Xingyuan Zhang, Patrick van der Smagt, Philip Becker-Ehmck · 12 de diciembre de 2025

  Inspired by how humans combine direct interaction with action-free experience (e.g., videos), we study world models that learn from heterogeneous data. Standard world models typically rely on action-conditioned trajectories, which limits effectiveness when action labels are scarce. We introduce a fa…

• An M-Health Algorithmic Approach to Identify and Assess Physiotherapy Exercises in Real Time

  Stylianos Kandylakis, Christos Orfanopoulos, Georgios Siolas, Panayiotis Tsanakas · 12 de diciembre de 2025

  This work presents an efficient algorithmic framework for real-time identification, classification, and evaluation of human physiotherapy exercises using mobile devices. The proposed method interprets a kinetic movement as a sequence of static poses, which are estimated from camera input using a pos…

• AugLift: Uncertainty Aware Depth Descriptors for Robust 2D to 3D Pose Lifting

  Nikolai Warner, Wenjin Zhang, Hamid Badiozamani, Irfan Essa, Apaar Sadhwani · 11 de diciembre de 2025

  Lifting based 3D human pose estimators infer 3D joints from 2D keypoints, but often struggle to generalize to real world settings with noisy 2D detections. We revisit the input to lifting and propose AugLift, a simple augmentation of standard lifting that enriches each 2D keypoint (x, y) with an Unc…

• What Happens When: Learning Temporal Orders of Events in Videos

  Daechul Ahn, Yura Choi, Hyeonbeom Choi, Seongwon Cho, San Kim, Jonghyun Choi · 11 de diciembre de 2025

  Video Large Multimodal Models (VLMMs) have shown impressive performance in video understanding, yet their ability to accurately capture the temporal order of multiple events remains underexplored. We interestingly observe that, even when video frames are scrambled, models perform very well on the ex…

• Exploring Ordinal Bias in Action Recognition for Instructional Videos

  Joochan Kim, Minjoon Jung, Byoung-Tak Zhang · 8 de diciembre de 2025

  Action recognition models have achieved promising results in understanding instructional videos. However, they often rely on dominant, dataset-specific action sequences rather than true video comprehension, a problem that we define as ordinal bias. To address this issue, we propose two effective vid…

• Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations

  Nicola Messina, Rosario Leonardi, Luca Ciampi, Fabio Carrara, Giovanni Maria Farinella, Fabrizio Falchi, Antonino Furnari · 3 de diciembre de 2025

  Pixel-level recognition of objects manipulated by the user from egocentric images enables key applications spanning assistive technologies, industrial safety, and activity monitoring. However, progress in this area is currently hindered by the scarcity of annotated datasets, as existing approaches r…

• DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions

  Yifan Zhou, Takehiko Ohkawa, Guwenxiao Zhou, Kanoko Goto, Takumi Hirose, Yusuke Sekikawa, Nakamasa Inoue · 3 de diciembre de 2025

  Modeling daily hand interactions often struggles with severe occlusions, such as when two hands overlap, which highlights the need for robust feature learning in 3D hand pose estimation (HPE). To handle such occluded hand images, it is vital to effectively learn the relationship between local image …

• Multivariate Gaussian Representation Learning for Medical Action Evaluation

  Luming Yang, Haoxian Liu, Siqing Li, Alper Yilmaz · 2 de diciembre de 2025

  Fine-grained action evaluation in medical vision faces unique challenges due to the unavailability of comprehensive datasets, stringent precision requirements, and insufficient spatiotemporal dynamic modeling of very rapid actions. To support development and evaluation, we introduce CPREval-6k, a mu…

• Learning to Generate Rigid Body Interactions with Video Diffusion Models

  David Romero, Ariana Bermudez, Hao Li, Fabio Pizzati, Ivan Laptev · 2 de diciembre de 2025

  Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, however, cur…

• Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation

  Mengshi Qi, Jiaxuan Peng, Xianlin Zhang, Huadong Ma · 2 de diciembre de 2025

  3D human pose estimation (3D HPE) has emerged as a prominent research topic, particularly in the realm of RGB-based methods. However, the use of RGB images is often limited by issues such as occlusion and privacy constraints. Consequently, multi-modal sensing, which leverages non-intrusive sensors, …

• Integrating Skeleton Based Representations for Robust Yoga Pose Classification Using Deep Learning Models

  Mohammed Mohiuddin, Syed Mohammod Minhaz Hossain, Sumaiya Khanam, Prionkar Barua, Aparup Barua, MD Tamim Hossain · 2 de diciembre de 2025

  Yoga is a popular form of exercise worldwide due to its spiritual and physical health benefits, but incorrect postures can lead to injuries. Automated yoga pose classification has therefore gained importance to reduce reliance on expert practitioners. While human pose keypoint extraction models have…