{"total":58,"rows":[{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77,"area":null},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67,"area":null},{"id":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2301.09152","title":"Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data","created":"2023-01-22","cited_by_count":40,"area":null},{"id":"2403.17103","title":"Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos","created":"2024-03-25","cited_by_count":26,"area":null},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"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":"2412.00837","title":"AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer","created":"2024-12-01","cited_by_count":20,"area":null},{"id":"2406.11933","title":"Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2310.05056","title":"Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching","created":"2023-10-08","cited_by_count":11,"area":null},{"id":"2511.01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction","created":"2025-11-03","cited_by_count":9,"area":null},{"id":"2508.00298","title":"AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformer","created":"2025-08-01","cited_by_count":7,"area":null},{"id":"2506.20983","title":"Rethink Sparse Signals for Pose-guided Text-to-image Generation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2509.08800","title":"PianoVAM: A Multimodal Piano Performance Dataset","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2405.14002","title":"Animal Behavior Analysis Methods Using Deep Learning: A Survey","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2406.14367","title":"PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2504.19863","title":"Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2507.02565","title":"Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2608.06009","title":"Wan-Animate-2: Pushing the Application Boundaries of Character Animation","created":"2026-08-06","cited_by_count":4,"area":null},{"id":"2503.16120","title":"Probabilistic Prompt Distribution Learning for Animal Pose Estimation","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2510.03532","title":"Efficient Surgical Robotic Instrument Pose Reconstruction in Real World Conditions Using Unified Feature Detection","created":"2025-10-03","cited_by_count":3,"area":null},{"id":"2408.10831","title":"ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2603.10125","title":"4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2501.01174","title":"L3D-Pose: Lifting Pose for 3D Avatars from a Single Camera in the Wild","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2504.08175","title":"Multi-person Physics-based Pose Estimation for Combat Sports","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2505.17475","title":"PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2507.02771","title":"Grounding Intelligence in Movement","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2508.18238","title":"PriorFormer: A Transformer for Real-time Monocular 3D Human Pose Estimation with Versatile Geometric Priors","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2511.04255","title":"MedSapiens: Taking a Pose to Rethink Medical Imaging Landmark Detection","created":"2025-11-06","cited_by_count":1,"area":null},{"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":"2601.09698","title":"COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation","created":"2026-01-14","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":"2607.07320","title":"SoccerNet 2026 Challenges Results","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2609.01823","title":"Kirin: Animal Motion Generation from In-the-Wild Video","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.35718","title":"Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2303.00891","title":"MoSS: Monocular Shape Sensing for Continuum Robots","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2306.10858","title":"Multi-Granularity Hand Action Detection","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2405.03141","title":"Automatic Ultrasound Curve Angle Measurement via Affinity Clustering for Adolescent Idiopathic Scoliosis Evaluation","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2501.18453","title":"Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2502.10616","title":"Learning semantical dynamics and spatiotemporal collaboration for human pose estimation in video","created":"2025-02-15","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":"2510.04654","title":"MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2511.16712","title":"PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2602.13901","title":"RPGD: RANSAC-P3P Gradient Descent for Extrinsic Calibration in 3D Human Pose Estimation","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.04874","title":"Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.01322","title":"Human Pose Estimation in Trampoline Gymnastics: How to Improve Performance on Extreme Poses","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.15221","title":"Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.15497","title":"AnyAct: Towards Human Reenactment of Character Motion From Video","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.06847","title":"Physics-Driven Semantic Scattering Structure Understanding of Aircraft Target in SAR Images","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.09390","title":"Real-time body pose non-verbal communication with a consistency-based reliability measure","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.00752","title":"GKDT: General Keypoint Detection Transformer","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.23803","title":"Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.01628","title":"Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.24130","title":"Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking","created":"2026-08-25","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":"2609.29106","title":"WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.29912","title":"Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}