{"total":185,"rows":[{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65,"area":null},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59,"area":null},{"id":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","cited_by_count":49,"area":null},{"id":"2303.05234","title":"GPGait: Generalized Pose-based Gait Recognition","created":"2023-03-09","cited_by_count":40,"area":null},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40,"area":null},{"id":"2307.13933","title":"AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception","created":"2023-07-26","cited_by_count":39,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2509.06607","title":"From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans","created":"2025-09-08","cited_by_count":27,"area":null},{"id":"2312.02137","title":"MANUS: Markerless Grasp Capture using Articulated 3D Gaussians","created":"2023-12-04","cited_by_count":26,"area":null},{"id":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2309.17209","title":"Robots That Can See: Leveraging Human Pose for Trajectory Prediction","created":"2023-09-29","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21,"area":null},{"id":"2303.12741","title":"A Method for Animating Children's Drawings of the Human Figure","created":"2023-03-07","cited_by_count":20,"area":null},{"id":"2407.01264","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","created":"2024-07-01","cited_by_count":20,"area":null},{"id":"2304.00553","title":"From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding","created":"2023-04-02","cited_by_count":19,"area":null},{"id":"2403.02563","title":"Systemic Biases in Sign Language AI Research: A Deaf-Led Call to Reevaluate Research Agendas","created":"2024-03-05","cited_by_count":19,"area":null},{"id":"2407.08634","title":"RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2308.06554","title":"Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction","created":"2023-08-12","cited_by_count":18,"area":null},{"id":"2403.02090","title":"Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations","created":"2024-03-04","cited_by_count":18,"area":null},{"id":"2306.11546","title":"Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2311.17891","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","created":"2023-11-29","cited_by_count":17,"area":null},{"id":"2303.05463","title":"Understanding the Challenges and Opportunities of Pose-based Anomaly Detection","created":"2023-03-09","cited_by_count":15,"area":null},{"id":"2311.01851","title":"Holistic Representation Learning for Multitask Trajectory Anomaly Detection","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2308.00519","title":"Markerless human pose estimation for biomedical applications: a survey","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2310.04189","title":"Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases","created":"2023-10-06","cited_by_count":13,"area":null},{"id":"2303.02413","title":"Improved Trajectory Reconstruction for Markerless Pose Estimation","created":"2023-03-04","cited_by_count":12,"area":null},{"id":"2306.07399","title":"4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements","created":"2023-06-12","cited_by_count":12,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2212.02710","title":"Beyond Object Recognition: A New Benchmark towards Object Concept Learning","created":"2022-12-06","cited_by_count":11,"area":null},{"id":"2308.10623","title":"GaitPT: Skeletons Are All You Need For Gait Recognition","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2310.10547","title":"InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2402.18844","title":"Deep learning for 3D human pose estimation and mesh recovery: A survey","created":"2024-02-29","cited_by_count":11,"area":null},{"id":"2411.14565","title":"Privacy-Preserving Video Anomaly Detection: A Survey","created":"2024-11-21","cited_by_count":11,"area":null},{"id":"2303.10654","title":"Markerless Motion Capture and Biomechanical Analysis Pipeline","created":"2023-03-19","cited_by_count":10,"area":null},{"id":"2406.00384","title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","created":"2024-06-01","cited_by_count":9,"area":null},{"id":"2503.10624","title":"ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2305.01241","title":"AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis","created":"2023-05-02","cited_by_count":8,"area":null},{"id":"2307.14889","title":"Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2311.02892","title":"Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images","created":"2023-11-06","cited_by_count":8,"area":null},{"id":"2311.16497","title":"GaitContour: Efficient Gait Recognition based on a Contour-Pose Representation","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2403.13667","title":"DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2504.10676","title":"H-MoRe: Learning Human-centric Motion Representation for Action Analysis","created":"2025-04-14","cited_by_count":8,"area":null},{"id":"2309.05073","title":"FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions","created":"2023-09-10","cited_by_count":7,"area":null},{"id":"2312.10714","title":"Primitive-based 3D Human-Object Interaction Modelling and Programming","created":"2023-12-17","cited_by_count":7,"area":null},{"id":"2406.02976","title":"DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2408.02285","title":"Joint-Motion Mutual Learning for Pose Estimation in Videos","created":"2024-08-05","cited_by_count":7,"area":null},{"id":"2504.09862","title":"RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence","created":"2025-04-14","cited_by_count":7,"area":null},{"id":"2506.18368","title":"Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2310.13039","title":"Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.09723","title":"Tracking Skiers from the Top to the Bottom","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2401.11790","title":"Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2406.01316","title":"Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2406.17382","title":"Automatic infant 2D pose estimation from videos: comparing seven deep neural network methods","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2407.10756","title":"GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2407.19497","title":"Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph","created":"2024-07-28","cited_by_count":6,"area":null},{"id":"2408.15185","title":"Human-Centric Video Anomaly Detection Through Spatio-Temporal Pose Tokenization and Transformer","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2410.19488","title":"MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2412.18874","title":"A Culturally-Aware Benchmark for Person Re-Identification in Modest Attire","created":"2024-12-25","cited_by_count":6,"area":null},{"id":"2211.14309","title":"FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2311.14775","title":"VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG","created":"2023-11-24","cited_by_count":5,"area":null},{"id":"2401.06757","title":"Synthetic Data Generation Framework, Dataset, and Efficient Deep Model for Pedestrian Intention Prediction","created":"2024-01-12","cited_by_count":5,"area":null},{"id":"2401.08472","title":"Instilling Multi-round Thinking to Text-guided Image Generation","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2405.16493","title":"Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2408.09333","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2411.06725","title":"GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correction","created":"2024-11-11","cited_by_count":5,"area":null},{"id":"2412.13393","title":"MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2502.05432","title":"MoFM: A Large-Scale Human Motion Foundation Model","created":"2025-02-08","cited_by_count":5,"area":null},{"id":"2302.09187","title":"Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer","created":"2023-02-17","cited_by_count":4,"area":null},{"id":"2303.00952","title":"Towards Activated Muscle Group Estimation in the Wild","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2309.00794","title":"FastPoseGait: A Toolbox and Benchmark for Efficient Pose-based Gait Recognition","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2311.05041","title":"Active Transfer Learning for Efficient Video-Specific Human Pose Estimation","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2401.17185","title":"Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses","created":"2024-01-30","cited_by_count":4,"area":null},{"id":"2407.13777","title":"DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2409.20223","title":"GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Prediction","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2503.12912","title":"Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2505.07012","title":"Hand-Shadow Poser","created":"2025-05-11","cited_by_count":4,"area":null},{"id":"2508.02168","title":"After the Party: Navigating the Mapping From Color to Ambient Lighting","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2406.00859","title":"Streaming quanta sensors for online, high-performance imaging and vision","created":"2024-06-02","cited_by_count":3,"area":null},{"id":"2408.06614","title":"ViMo: Generating Motions from Casual Videos","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2408.08182","title":"Your Turn: At Home Turning Angle Estimation for Parkinson's Disease Severity Assessment","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2412.05277","title":"Text to Blind Motion","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2412.18785","title":"Simultaneously Recovering Multi-Person Meshes and Multi-View Cameras with Human Semantics","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2502.12546","title":"Spatiotemporal Multi-Camera Calibration using Freely Moving People","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2510.21654","title":"Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2512.16360","title":"EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animation","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2603.23997","title":"HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2605.21957","title":"Bounding-Box Trajectories Matter for Video Anomaly Detection","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2303.18119","title":"Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2304.10765","title":"BPJDet: Extended Object Representation for Generic Body-Part Joint Detection","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2308.11484","title":"Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia","created":"2023-08-22","cited_by_count":2,"area":null}],"next_cursor":"100"}