{"total":64,"rows":[{"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":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"area":null},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117,"area":null},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105,"area":"diffusion"},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103,"area":null},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70,"area":null},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68,"area":null},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58,"area":null},{"id":"2303.17368","title":"SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling","created":"2023-03-30","cited_by_count":54,"area":null},{"id":"2312.08869","title":"I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions","created":"2023-12-10","cited_by_count":44,"area":null},{"id":"2403.17934","title":"AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation","created":"2024-03-26","cited_by_count":42,"area":null},{"id":"2209.08790","title":"D&D: Learning Human Dynamics from Dynamic Camera","created":"2022-09-19","cited_by_count":41,"area":null},{"id":"2303.13796","title":"Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction","created":"2023-03-24","cited_by_count":41,"area":null},{"id":"2408.00762","title":"UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model","created":"2024-08-01","cited_by_count":30,"area":null},{"id":"2203.08713","title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","created":"2022-03-16","cited_by_count":29,"area":null},{"id":"2404.04430","title":"PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos","created":"2024-04-05","cited_by_count":28,"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":"2308.13551","title":"Dance with You: The Diversity Controllable Dancer Generation via Diffusion Models","created":"2023-08-23","cited_by_count":17,"area":null},{"id":"2503.22906","title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models","created":"2025-03-28","cited_by_count":14,"area":null},{"id":"2512.11988","title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","created":"2025-12-12","cited_by_count":14,"area":null},{"id":"2308.10174","title":"Neural Interactive Keypoint Detection","created":"2023-08-20","cited_by_count":12,"area":null},{"id":"2304.07916","title":"GaitRef: Gait Recognition with Refined Sequential Skeletons","created":"2023-04-16","cited_by_count":9,"area":null},{"id":"2307.01200","title":"ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning","created":"2023-07-03","cited_by_count":9,"area":null},{"id":"2412.13111","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","created":"2024-12-17","cited_by_count":9,"area":null},{"id":"2505.01746","title":"Co$^{3}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion","created":"2025-05-03","cited_by_count":9,"area":null},{"id":"2307.09026","title":"ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting","created":"2023-07-18","cited_by_count":8,"area":null},{"id":"2404.10880","title":"HumMUSS: Human Motion Understanding using State Space Models","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2502.16175","title":"Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2512.23635","title":"Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2312.16221","title":"STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation","created":"2023-12-24","cited_by_count":2,"area":null},{"id":"2404.10383","title":"Learning to Score Sign Language with Two-stage Method","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2405.16874","title":"CoCoGesture: Toward Coherent Co-speech 3D Gesture Generation in the Wild","created":"2024-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2507.08038","title":"AblationBench: Evaluating Automated Planning of Ablations in Empirical AI Research","created":"2025-07-09","cited_by_count":2,"area":"agents"},{"id":"2512.20128","title":"milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion","created":"2025-12-23","cited_by_count":2,"area":"ssm"},{"id":"2404.02345","title":"GaitSTR: Gait Recognition with Sequential Two-stream Refinement","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2404.10490","title":"Enhancing Sign Language Teaching: A Mixed Reality Approach for Immersive Learning and Multi-Dimensional Feedback","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2409.00736","title":"MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds","created":"2024-09-01","cited_by_count":1,"area":null},{"id":"2503.06151","title":"Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and Estimation","created":"2025-03-08","cited_by_count":1,"area":"diffusion"},{"id":"2511.07412","title":"TwinOR: Photorealistic Digital Twins of Dynamic Operating Rooms for Embodied AI Research","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2512.21905","title":"High-Fidelity and Long-Duration Human Image Animation with Diffusion Transformer","created":"2025-12-26","cited_by_count":1,"area":"diffusion"},{"id":"2603.07697","title":"Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation","created":"2026-03-08","cited_by_count":1,"area":"diffusion"},{"id":"2603.14435","title":"End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2309.12183","title":"ORTexME: Occlusion-Robust Human Shape and Pose via Temporal Average Texture and Mesh Encoding","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2311.09543","title":"Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2311.11662","title":"Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2401.03914","title":"D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2405.12724","title":"RemoCap: Disentangled Representation Learning for Motion Capture","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2409.01555","title":"EA-RAS: Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2505.18048","title":"SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarios","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.21234","title":"Real-Time ESFP: Estimating, Smoothing, Filtering, and Pose-Mapping","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.11075","title":"Joint angle based learning to refine kinematic human pose estimation","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2508.06757","title":"VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2511.01756","title":"HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2601.00625","title":"RePose: A Real-Time 3D Human Pose Estimation and Biomechanical Analysis Framework for Rehabilitation","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2602.18199","title":"A Self-Supervised Approach on Motion Calibration for Enhancing Physical Plausibility in Text-to-Motion","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2604.13581","title":"SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.17959","title":"Chatting about Upper-Body Expressive Human Pose and Shape Estimation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.18557","title":"SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.24609","title":"Evaluation of Pose Estimation Systems for Sign Language Translation","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.22876","title":"Full-Body Golf Swing Kinematic Reconstruction From a Smartwatch IMU","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.29292","title":"PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}