{"total":69,"rows":[{"id":"2606.10804","title":"SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning","created":"2026-06-09","cited_by_count":8,"area":null},{"id":"2603.03265","title":"DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction","created":"2026-03-03","cited_by_count":7,"area":null},{"id":"2603.16858","title":"SOMA: Unifying Parametric Human Body Models","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2605.22144","title":"One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems","created":"2026-05-21","cited_by_count":6,"area":"agents"},{"id":"2606.06194","title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2605.09258","title":"Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Models","created":"2026-05-10","cited_by_count":5,"area":null},{"id":"2603.15603","title":"Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.19636","title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","created":"2026-04-21","cited_by_count":3,"area":"diffusion"},{"id":"2605.15477","title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","created":"2026-05-14","cited_by_count":3,"area":"wm"},{"id":"2605.20373","title":"SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.28625","title":"ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2602.16502","title":"DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2604.08294","title":"Can Vision Language Models Judge Action Quality? An Empirical Evaluation","created":"2026-04-09","cited_by_count":2,"area":"mllm"},{"id":"2604.18468","title":"Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation","created":"2026-04-20","cited_by_count":2,"area":"driving"},{"id":"2606.27720","title":"Scene and Human in One World: Reconstruction in a Feedforward Pass","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2604.01447","title":"Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.08921","title":"TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.17120","title":"Markerless Motion Capture for Biomechanical Whole-Body Kinematic Estimation in Infants","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2606.02366","title":"PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.20891","title":"Go-with-the-Track: Video Compositing and Motion Control with Point Tracking","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.29083","title":"MHRGait: Gait Recognition from Momentum Human Rig Pose","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2608.20335","title":"4DAnyone: Create Anyone in 4D from a Casual Monocular Video","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.29928","title":"Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.00369","title":"Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2603.11257","title":"Towards Automated Initial Probe Placement in Transthoracic Teleultrasound Using Human Mesh and Skeleton Recovery","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.17178","title":"Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Video","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.29101","title":"Enhancing Box and Block Test with Computer Vision for Post-Stroke Upper Extremity Motor Evaluation","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.07331","title":"RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.12923","title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.18648","title":"DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.20800","title":"LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.25646","title":"SAMe: A Semantic Anatomy Mapping Engine for Robotic Ultrasound","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.14462","title":"Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.22629","title":"H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.29953","title":"Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31551","title":"SMART: SMPLest-X Mesh Adaptation and RAFT Tracking for Soccer Pose Estimation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.04291","title":"A Cookbook of 3D Vision: Data, Learning Paradigms, and Application","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.06631","title":"From Pixels to Newtons: Predicting In Vivo Joint Contact Forces from Monocular Video","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.07419","title":"DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.11739","title":"Multi-View In-Cabin Monitoring System for Public Transport Vehicles","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.31981","title":"LUNA: Learning Universal 3D Human Animation Beyond Skinning","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02796","title":"Biomechanics-aware Multi-view Markerless Motion Capture of Dexterous Hand Movements","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.06691","title":"CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.07357","title":"HumAIN: Human-Aware Implicit Social Robot Navigation","created":"2026-07-08","cited_by_count":0,"area":"distill"},{"id":"2607.12450","title":"Let RGB Be the Language of Vision","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.13472","title":"EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.17639","title":"Direct Clinical Joint Angle Extraction from Parametric Body Model Rotation Matrices","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.22973","title":"mmSimPrior: Learning Simulation Priors for Data-Efficient and Generalizable Real-World Radar-based Human Motion Reconstruction","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2607.23608","title":"Markerless Motion Capture in Routine Clinical Upper Limb Assessments: Validity and Insights Beyond Ordinal Scoring","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.23657","title":"GRAPE: Graduated Routing for Articulated Portrait mesh Estimation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.01944","title":"UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.27407","title":"Reconstructing Humans and Objects in Interaction using Large Reconstruction Models","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.28386","title":"GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.29927","title":"Everybody Tracking Every Body","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01840","title":"Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02854","title":"MuyBridge: Mobile Human Center-of-Mass Estimation from Monocular Video via Sparse Fusion","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.10498","title":"Field Converter: Geometry-Initialized Temporal Residual Refinement for World-Grounded Player Pose Estimation from Soccer Broadcasts","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.18406","title":"Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.34768","title":"Privacy-Preserving Full-Body Meshing from mmWave Radar via Mesh Foundation Model Supervision","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34978","title":"One Sensor, Whole Body - 3D Body Pose from a Single Consumer Earbud IMU","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35764","title":"Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Pose","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00451","title":"PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03691","title":"FlowHMR: Physically Plausible Motion Capture from Video","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06972","title":"BoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action Feedback","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.12895","title":"MeshBind: Point-to-Mesh Binding for Non-Rigid Scene Flow Automatic Annotation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19729","title":"A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20124","title":"DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}