Human Pose and Action Recognition

Últimos artículos

• MorphArtGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping

  Heng Zhang, Kevin Yuchen Ma, Mike Zheng Shou, Weisi Lin, Yan Wu · 3 de marzo de 2026

  Dexterous grasping with multi-fingered hands remains challenging due to high-dimensional articulations and the cost of optimization-based pipelines. Existing end-to-end methods require training on large-scale datasets for specific hands, limiting their ability to generalize across different embodime…

• SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistency

  Yeonsung Kim, Junggeun Do, Seunguk Do, Sangmin Kim, Jaesik Park, Jay-Yoon Lee · 24 de febrero de 2026

  3D human pose estimation (HPE) is characterized by intricate local and global dependencies among joints. Conventional supervised losses are limited in capturing these correlations because they treat each joint independently. Previous studies have attempted to promote structural consistency through m…

• DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE

  Yujie Jin, Wenxin Zhang, Jingjing Wang, Guodong Zhou · 23 de febrero de 2026

  In the literature, prior research on Security-oriented Video Understanding (SVU) has predominantly focused on detecting and localize the threats (e.g., shootings, robberies) in videos, while largely lacking the effective capability to generate and evaluate the threat causes. Motivated by these gaps,…

• Align and Adapt: Multimodal Multiview Human Activity Recognition under Arbitrary View Combinations

  Duc-Anh Nguyen, Nhien-An Le-Khac · 19 de febrero de 2026

  Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, numbers of views, and heterogeneous modalities. Focusing on the context of human…

• Factored Latent Action World Models

  Zizhao Wang, Chang Shi, Jiaheng Hu, Kevin Rohling, Roberto Mart\'in-Mart\'in, Amy Zhang, Peter Stone · 19 de febrero de 2026

  Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However, most existing approaches rely on monolithic inverse and for…

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories

  Praditha Alwis, Soumyadeep Chandra, Deepak Ravikumar, Kaushik Roy · 18 de febrero de 2026

  High-quality video datasets are foundational for training robust models in tasks like action recognition, phase detection, and event segmentation. However, many real-world video datasets suffer from annotation errors such as *mislabeling*, where segments are assigned incorrect class labels, and *dis…

• Time-Archival Camera Virtualization for Sports and Visual Performances

  Yunxiao Zhang, William Stone, Suryansh Kumar · 18 de febrero de 2026

  Camera virtualization -- an emerging solution to novel view synthesis -- holds transformative potential for visual entertainment, live performances, and sports broadcasting by enabling the generation of photorealistic images from novel viewpoints using images from a limited set of calibrated multipl…

• RPGD: RANSAC-P3P Gradient Descent for Extrinsic Calibration in 3D Human Pose Estimation

  Zhanyu Tuo · 17 de febrero de 2026

  In this paper, we propose RPGD (RANSAC-P3P Gradient Descent), a human-pose-driven extrinsic calibration framework that robustly aligns MoCap-based 3D skeletal data with monocular or multi-view RGB cameras using only natural human motion. RPGD formulates extrinsic calibration as a coarse-to-fine prob…

• How to Sample High Quality 3D Fractals for Action Recognition Pre-Training?

  Marko Putak, Thomas B. Moeslund, Joakim Bruslund Haurum · 13 de febrero de 2026

  Synthetic datasets are being recognized in the deep learning realm as a valuable alternative to exhaustively labeled real data. One such synthetic data generation method is Formula Driven Supervised Learning (FDSL), which can provide an infinite number of perfectly labeled data through a formula dri…

• Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations

  Firas Darwish, George Nicholson, Aiden Doherty, Hang Yuan · 12 de febrero de 2026

  Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data often fail to transfer reliably to deployment settings. We study this problem in full-body human motion, where large-scale data collection is infeasible but essenti…

• Olaf-World: Orienting Latent Actions for Video World Modeling

  Yuxin Jiang, Yuchao Gu, Ivor W. Tsang, Mike Zheng Shou · 11 de febrero de 2026

  Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control interfaces from unlabeled video, learned latents often fail to transfer across contexts: they entangle scene-specific cues and lack a shared coordinate syste…

• Gesture Matters: Pedestrian Gesture Recognition for AVs Through Skeleton Pose Evaluation

  Alif Rizqullah Mahdi, Mahdi Rezaei, Natasha Merat · 10 de febrero de 2026

  Gestures are a key component of non-verbal communication in traffic, often helping pedestrian-to-driver interactions when formal traffic rules may be insufficient. This problem becomes more apparent when autonomous vehicles (AVs) struggle to interpret such gestures. In this study, we present a gestu…

• GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing

  Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin · 10 de febrero de 2026

  Human perception for effective object tracking in a 2D video stream arises from the implicit use of prior 3D knowledge combined with semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the target and its surroundings while neglecting 3D geomet…

• MIND: Benchmarking Memory Consistency and Action Control in World Models

  Yixuan Ye, Xuanyu Lu, Yuxin Jiang, Yuchao Gu, Rui Zhao, Qiwei Liang, Jiachun Pan, Fengda Zhang, Weijia Wu, Alex Jinpeng Wang · 10 de febrero de 2026

  World models aim to understand, remember, and predict dynamic visual environments, yet a unified benchmark for evaluating their fundamental abilities remains lacking. To address this gap, we introduce MIND, the first open-domain closed-loop revisited benchmark for evaluating Memory consIstency and a…

• Redundancy-Free View Alignment for Multimodal Human Activity Recognition with Arbitrarily Missing Views

  Duc-Anh Nguyen, Nhien-An Le-Khac · 10 de febrero de 2026

  Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, numbers of views, and heterogeneous modalities. Focusing on the context of human…

• BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents

  R. James Cotton, Thomas Leonard · 10 de febrero de 2026

  Markerless motion capture is making quantitative movement analysis increasingly accessible, yet analyzing the resulting data remains a barrier for clinicians without programming expertise. We present BiomechAgent, a code-generating AI agent that enables biomechanical analysis through natural languag…

• Action-to-Action Flow Matching

  Jindou Jia, Gen Li, Xiangyu Chen, Tuo An, Yuxuan Hu, Jingliang Li, Xinying Guo, Jianfei Yang · 10 de febrero de 2026

  Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice of sampling from random Gaussian noise often requires multiple iterative steps to produce clean actions, leading to high …

• TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation

  Yuanzhi Liang, Xuan'er Wu, Yirui Liu, Yijie Fang, Yizhen Fan, Ke Hao, Rui Li, Ruiying Liu, Ziqi Ni, Peng Yu, Yanbo Wang, Haibin Huang, Qizhen Weng, Chi Zhang, Xuelong Li · 10 de febrero de 2026

  Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long temporal horizons. This report presents a systematical post-training framework that organizes supervised policy shaping, r…

• ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning

  Aman Anand, Amir Eskandari, Elyas Rahsno, Farhana Zulkernine · 9 de febrero de 2026

  Self-supervised learning (SSL) has shown remarkable success in skeleton-based action recognition by leveraging data augmentations to learn meaningful representations. However, existing SSL methods rely on data augmentations that predominantly focus on masking high-motion frames and high-degree joint…

• Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics

  Ruizhe Zhong, Jiesong Lian, Xiaoyue Mi, Zixiang Zhou, Yuan Zhou, Qinglin Lu, Junchi Yan · 6 de febrero de 2026

  While online Reinforcement Learning has emerged as a crucial technique for aligning flow matching models with human preferences, current approaches are hindered by inefficient exploration during training rollouts. Relying on undirected stochasticity and sparse outcome rewards, these methods struggle…

• HoloEv-Net: Efficient Event-based Action Recognition via Holographic Spatial Embedding and Global Spectral Gating

  Weidong Hao · 5 de febrero de 2026

  Event-based Action Recognition (EAR) has attracted significant attention due to the high temporal resolution and high dynamic range of event cameras. However, existing methods typically suffer from (i) the computational redundancy of dense voxel representations, (ii) structural redundancy inherent i…

• Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms

  Yiran Qiao, Jing Chen, Xiang Ao, Qiwei Zhong, Yang Liu, Qing He · 4 de febrero de 2026

  Live streaming has become a cornerstone of today's internet, enabling massive real-time social interactions. However, it faces severe risks arising from sparse, coordinated malicious behaviors among multiple participants, which are often concealed within normal activities and challenging to detect t…

• On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning

  Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau, S\'ebastien Lachapelle · 4 de febrero de 2026

  Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. Some SSIL methods learn an inverse dynamics model (IDM) to predict the action from the current state and the next state. …

• InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction

  Sirui Xu, Ziyin Wang, Yu-Xiong Wang, Liang-Yan Gui · 3 de febrero de 2026

  Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic human-object interaction (HOI) generation faces notable challenges, pr…

• Segment to Focus: Guiding Latent Action Models in the Presence of Distractors

  Hamza Adnan, Matthew T. Jackson, Alexey Zakharov · 3 de febrero de 2026

  Latent Action Models (LAMs) learn to extract action-relevant representations solely from raw observations, enabling reinforcement learning from unlabelled videos and significantly scaling available training data. However, LAMs face a critical challenge in disentangling action-relevant features from …