{"total":22,"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":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227,"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":"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":"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":"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":"2407.11321","title":"TCFormer: Visual Recognition via Token Clustering Transformer","created":"2024-07-16","cited_by_count":12,"area":null},{"id":"2312.05525","title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception","created":"2023-12-09","cited_by_count":9,"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":"2407.16341","title":"Motion Capture from Inertial and Vision Sensors","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2404.19401","title":"UniFS: Universal Few-shot Instance Perception with Point Representations","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2602.17768","title":"KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2407.10220","title":"PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2603.09418","title":"CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2407.14903","title":"Automated Patient Positioning with Learned 3D Hand Gestures","created":"2024-07-20","cited_by_count":0,"area":null},{"id":"2411.10334","title":"Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2502.20803","title":"Two-Stream Spatial-Temporal Transformer Framework for Person Identification via Natural Conversational Keypoints","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2510.00049","title":"AI-Based Stroke Rehabilitation Domiciliary Assessment System with ST_GCN Attention","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2602.08479","title":"Gesture Matters: Pedestrian Gesture Recognition for AVs Through Skeleton Pose Evaluation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.09681","title":"Improving 3D Foot Motion Reconstruction in Markerless Monocular Human Motion Capture","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.20391","title":"Monocular Models are Strong Learners for Multi-View Human Mesh Recovery","created":"2026-03-20","cited_by_count":0,"area":null}],"next_cursor":null}