Human Pose and Action Recognition

Últimos artículos

• PSDNorm: Test-Time Temporal Normalization for Deep Learning in Sleep Staging

  Th\'eo Gnassounou, Antoine Collas, R\'emi Flamary, Alexandre Gramfort · 2 de febrero de 2026

  Distribution shift poses a significant challenge in machine learning, particularly in biomedical applications using data collected across different subjects, institutions, and recording devices, such as sleep data. While existing normalization layers, BatchNorm, LayerNorm and InstanceNorm, help miti…

• PEAR: Pixel-aligned Expressive humAn mesh Recovery

  Jiahao Wu, Yunfei Liu, Lijian Lin, Ye Zhu, Lei Zhu, Jingyi Li, Yu Li · 2 de febrero de 2026

  Reconstructing detailed 3D human meshes from a single in-the-wild image remains a fundamental challenge in computer vision. Existing SMPLX-based methods often suffer from slow inference, produce only coarse body poses, and exhibit misalignments or unnatural artifacts in fine-grained regions such as …

• MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption

  Chen Li, Zhantao Yang, Han Zhang, Fangyi Chen, Chenchen Zhu, Anudeepsekhar Bolimera, Marios Savvides · 28 de enero de 2026

  Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA, a unified, backbone-agnostic post-training framework for eff…

• PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation

  Zongyou Yang, Jonathan Loo, Yinghan Hou · 28 de enero de 2026

  Recently, a significant improvement in the accuracy of 3D human pose estimation has been achieved by combining convolutional neural networks (CNNs) with pyramid grid alignment feedback loops. Additionally, innovative breakthroughs have been made in the field of computer vision through the adoption o…

• Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering

  Louie Hong Yao, Nicholas Jarvis, Tianyu Jiang · 27 de enero de 2026

  Evaluating visual activity recognition systems is challenging due to inherent ambiguities in verb semantics and image interpretation. When describing actions in images, synonymous verbs can refer to the same event (e.g., brushing vs. grooming), while different perspectives can lead to equally valid …

• Summary of the Unusual Activity Recognition Challenge for Developmental Disability Support

  Christina Garcia, Nhat Tan Le, Taihei Fujioka, Umang Dobhal, Milyun Ni'ma Shoumi, Thanh Nha Nguyen, Sozo Inoue · 27 de enero de 2026

  This paper presents an overview of the Recognize the Unseen: Unusual Behavior Recognition from Pose Data Challenge, hosted at ISAS 2025. The challenge aims to address the critical need for automated recognition of unusual behaviors in facilities for individuals with developmental disabilities using …

• Two-Stream temporal transformer for video action classification

  Nattapong Kurpukdee, Adrian G. Bors · 21 de enero de 2026

  Motion representation plays an important role in video understanding and has many applications including action recognition, robot and autonomous guidance or others. Lately, transformer networks, through their self-attention mechanism capabilities, have proved their efficiency in many applications. …

• Unsupervised Video Class-Incremental Learning via Deep Embedded Clustering Management

  Nattapong Kurpukdee, Adrian G. Bors · 21 de enero de 2026

  Unsupervised video class incremental learning (uVCIL) represents an important learning paradigm for learning video information without forgetting, and without considering any data labels. Prior approaches have focused on supervised class-incremental learning, relying on using the knowledge of labels…

• Variational Contrastive Learning for Skeleton-based Action Recognition

  Dang Dinh Nguyen, Decky Aspandi Latif, Titus Zaharia · 13 de enero de 2026

  In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently discriminative and often struggle to capture the variability and uncertainty intrins…

• Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification

  Ahmed Abdelkawy, Ahmed Elsayed, Asem Ali, Aly Farag, Thomas Tretter, Michael McIntyre · 13 de enero de 2026

  Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predicting student engagement typically require substantial annotated data to model the diversity of student behaviors, yet privacy concerns often restrict re…

• Mon3tr: Monocular 3D Telepresence with Pre-built Gaussian Avatars as Amortization

  Fangyu Lin, Yingdong Hu, Zhening Liu, Yufan Zhuang, Zehong Lin, Jun Zhang · 13 de enero de 2026

  Immersive telepresence aims to transform human interaction in AR/VR applications by enabling lifelike full-body holographic representations for enhanced remote collaboration. However, existing systems rely on hardware-intensive multi-camera setups and demand high bandwidth for volumetric streaming, …

• TRec: Learning Hand-Object Interactions through 2D Point Track Motion

  Dennis Holzmann, Sven Wachsmuth · 12 de enero de 2026

  We present a novel approach for hand-object action recognition that leverages 2D point tracks as an additional motion cue. While most existing methods rely on RGB appearance, human pose estimation, or their combination, our work demonstrates that tracking randomly sampled image points across video f…

• CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

  Peng Chen, Pi Bu, Yingyao Wang, Xinyi Wang, Ziming Wang, Jie Guo, Yingxiu Zhao, Qi Zhu, Jun Song, Siran Yang, Jiamang Wang, Bo Zheng · 12 de enero de 2026

  Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making in complex 3D environments, which demand second-level responses, high-resolution perception, and tactical reasoning und…

• TRec: Egocentric Action Recognition using 2D Point Tracks

  Dennis Holzmann, Sven Wachsmuth · 8 de enero de 2026

  We present a novel approach for egocentric action recognition that leverages 2D point tracks as an additional motion cue. While most existing methods rely on RGB appearance, human pose estimation, or their combination, our work demonstrates that tracking randomly sampled image points across video fr…

• EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos

  Hongming Fu, Wenjia Wang, Xiaozhen Qiao, Shuo Yang, Zheng Liu, Bo Zhao · 6 de enero de 2026

  We propose EgoGrasp, the first method to reconstruct world-space hand-object interactions (W-HOI) from egocentric monocular videos with dynamic cameras in the wild. Accurate W-HOI reconstruction is critical for understanding human behavior and enabling applications in embodied intelligence and virtu…

• Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning

  Shangzhe Li, Zhiao Huang, Hao Su · 6 de enero de 2026

  Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods often face instability challenges, particularly when relying …

• Lifelong Domain Adaptive 3D Human Pose Estimation

  Qucheng Peng, Hongfei Xue, Pu Wang, Chen Chen · 1 de enero de 2026

  3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D data collected in controlled environments poses challenges for generalization to diverse in-the-wild scenarios. Existing …

• ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning

  Bangya Liu, Xinyu Gong, Zelin Zhao, Ziyang Song, Yulei Lu, Suhui Wu, Jun Zhang, Suman Banerjee, Hao Zhang · 30 de diciembre de 2025

  Human-object interaction (HOI) video generation has garnered increasing attention due to its promising applications in digital humans, e-commerce, advertising, and robotics imitation learning. However, existing methods face two critical limitations: (1) a lack of effective mechanisms to inject multi…

• Next Best View Selections for Semantic and Dynamic 3D Gaussian Splatting

  Yiqian Li, Wen Jiang, Kostas Daniilidis · 30 de diciembre de 2025

  Understanding semantics and dynamics has been crucial for embodied agents in various tasks. Both tasks have much more data redundancy than the static scene understanding task. We formulate the view selection problem as an active learning problem, where the goal is to prioritize frames that provide t…

• EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation

  Libo Zhang, Zekun Li, Tianyu Li, Zeyu Cao, Rui Xu, Xiaoxiao Long, Wenjia Wang, Jingbo Wang, Yuan Liu, Wenping Wang, Daquan Zhou, Taku Komura, Zhiyang Dou · 30 de diciembre de 2025

  Humans exhibit adaptive, context-sensitive responses to egocentric visual input. However, faithfully modeling such reactions from egocentric video remains challenging due to the dual requirements of strictly causal generation and precise 3D spatial alignment. To tackle this problem, we first constru…

• Multi-Focused Video Group Activities Hashing

  Zhongmiao Qi, Yan Jiang, Bolin Zhang, Chong Wang, Lijun Guo, Pengjiang Qian, Jiangbo Qian · 30 de diciembre de 2025

  With the explosive growth of video data in various complex scenarios, quickly retrieving group activities has become an urgent problem. However, many tasks can only retrieve videos focusing on an entire video, not the activity granularity. To solve this problem, we propose a new STVH (spatiotemporal…

• Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition

  Naichuan Zheng, Xiahai Lun, Weiyi Li, Yuchen Du · 30 de diciembre de 2025

  Graph Convolutional Networks (GCNs) demonstrate strong capability in modeling skeletal topology for action recognition, yet their dense floating-point computations incur high energy costs. Spiking Neural Networks (SNNs), characterized by event-driven and sparse activation, offer energy efficiency bu…

• Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models

  Zheng Xing, Weibing Zhao · 30 de diciembre de 2025

  Unsupervised human motion segmentation (HMS) can be effectively achieved using subspace clustering techniques. However, traditional methods overlook the role of temporal semantic exploration in HMS. This paper explores the use of temporal vision semantics (TVS) derived from human motion sequences, l…

• DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors

  Kaustubh Kundu, Hrishav Bakul Barua, Lucy Robertson-Bell, Zhixi Cai, Kalin Stefanov · 25 de diciembre de 2025

  The trend in sign language generation is centered around data-driven generative methods that require vast amounts of precise 2D and 3D human pose data to achieve an acceptable generation quality. However, currently, most sign language datasets are video-based and limited to automatically reconstruct…

• FERA: A Pose-Based Semantic Pipeline for Automated Foil Fencing Refereeing

  Ziwen Chen, Zhong Wang · 25 de diciembre de 2025

  Many multimedia tasks map raw video into structured semantic representations for downstream decision-making. Sports officiating is a representative case, where fast, subtle interactions must be judged via symbolic rules. We present FERA (FEncing Referee Assistant), a pose-based framework that turns …