{"total":175,"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":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2410.00086","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","created":"2024-09-30","cited_by_count":56,"area":"diffusion"},{"id":"2501.15187","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","created":"2025-01-25","cited_by_count":56,"area":null},{"id":"2509.20360","title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","created":"2025-09-24","cited_by_count":54,"area":null},{"id":"2504.01724","title":"DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance","created":"2025-04-02","cited_by_count":36,"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":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2403.07304","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","created":"2024-03-12","cited_by_count":24,"area":"mllm"},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21,"area":null},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20,"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":"2403.17610","title":"MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2404.12347","title":"AniClipart: Clipart Animation with Text-to-Video Priors","created":"2024-04-18","cited_by_count":17,"area":null},{"id":"2406.10447","title":"The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences","created":"2024-06-14","cited_by_count":17,"area":null},{"id":"2508.02807","title":"DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework","created":"2025-08-04","cited_by_count":17,"area":"diffusion"},{"id":"2403.03270","title":"Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Tasks","created":"2024-03-05","cited_by_count":16,"area":"offlinerl"},{"id":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"area":null},{"id":"2405.19917","title":"Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition","created":"2024-05-30","cited_by_count":14,"area":"distill"},{"id":"2503.07499","title":"AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2508.00599","title":"DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior","created":"2025-08-01","cited_by_count":13,"area":"diffusion"},{"id":"2412.02317","title":"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset","created":"2024-12-03","cited_by_count":12,"area":null},{"id":"2506.00129","title":"Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation","created":"2025-05-30","cited_by_count":12,"area":null},{"id":"2312.10758","title":"SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation","created":"2023-12-17","cited_by_count":11,"area":null},{"id":"2501.16751","title":"HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging","created":"2025-01-28","cited_by_count":11,"area":null},{"id":"2406.11253","title":"Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2403.11111","title":"Diffusion Models are Efficient Data Generators for Human Mesh Recovery","created":"2024-03-17","cited_by_count":8,"area":"diffusion"},{"id":"2411.03561","title":"Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data","created":"2024-11-05","cited_by_count":8,"area":"diffusion"},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","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":"2312.09641","title":"Ins-HOI: Instance Aware Human-Object Interactions Recovery","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2403.05125","title":"Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2409.19580","title":"High Quality Human Image Animation using Regional Supervision and Motion Blur Condition","created":"2024-09-29","cited_by_count":7,"area":"diffusion"},{"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":"2411.08753","title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","created":"2024-11-13","cited_by_count":6,"area":null},{"id":"2407.16394","title":"SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2504.10035","title":"TT3D: Table Tennis 3D Reconstruction","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2504.21855","title":"ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling","created":"2025-04-30","cited_by_count":5,"area":"diffusion"},{"id":"2505.02481","title":"Finger Pose Estimation for Under-screen Fingerprint Sensor","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2512.21252","title":"DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation","created":"2025-12-24","cited_by_count":5,"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":"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":"2503.18282","title":"TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2505.01257","title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2505.22977","title":"HyperMotionX: The Dataset and Benchmark with DiT-Based Pose-Guided Human Image Animation of Complex Motions","created":"2025-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2510.24464","title":"Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras","created":"2025-10-28","cited_by_count":4,"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":"2410.09885","title":"Occluded Human Pose Estimation based on Limb Joint Augmentation","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2410.18723","title":"VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimation","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2411.04469","title":"FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2507.10223","title":"ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users","created":"2025-07-14","cited_by_count":3,"area":null},{"id":"2509.24980","title":"SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation","created":"2025-09-29","cited_by_count":3,"area":"diffusion"},{"id":"2603.18912","title":"GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2603.29931","title":"Gloria: Consistent Character Video Generation via Content Anchors","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2605.17179","title":"iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.31249","title":"Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2501.15763","title":"NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2502.20811","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","created":"2025-02-28","cited_by_count":2,"area":"mllm"},{"id":"2502.21085","title":"BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2503.21692","title":"RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2504.05700","title":"Pose-Aware Weakly-Supervised Action Segmentation","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2505.04713","title":"Comparison of Visual Trackers for Biomechanical Analysis of Running","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2505.05475","title":"SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation","created":"2025-05-08","cited_by_count":2,"area":"diffusion"},{"id":"2506.14428","title":"Toward Rich Video Human-Motion2D Generation","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.02713","title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation","created":"2025-07-03","cited_by_count":2,"area":"diffusion"},{"id":"2508.13562","title":"Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.21096","title":"ROBUST-MIPS: A Combined Skeletal Pose and Instance Segmentation Dataset for Laparoscopic Surgical Instruments","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.09946","title":"Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregation","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2511.17045","title":"RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2512.14162","title":"FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2512.15488","title":"RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting","created":"2025-12-17","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":"2603.11072","title":"OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.23617","title":"M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2608.11574","title":"Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2408.08623","title":"SketchRef: a Multi-Task Evaluation Benchmark for Sketch Synthesis","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2408.09240","title":"RepControlNet: ControlNet Reparameterization","created":"2024-08-17","cited_by_count":1,"area":"diffusion"},{"id":"2409.20469","title":"PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2412.01422","title":"MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection","created":"2024-12-02","cited_by_count":1,"area":"ssm"},{"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":"2501.18478","title":"SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Images","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2503.12485","title":"Cross-Modal Consistency Learning for Sign Language Recognition","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2503.13344","title":"STEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.08110","title":"Towards Unconstrained 2D Pose Estimation of the Human Spine","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2506.19747","title":"Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2507.12292","title":"Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation","created":"2025-07-16","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":"2509.21291","title":"VC-Agent: An Interactive Agent for Customized Video Dataset Collection","created":"2025-09-25","cited_by_count":1,"area":"agents"},{"id":"2510.19170","title":"FootFormer: Estimating Stability from Visual Input","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2511.10060","title":"Multivariate Gaussian Representation Learning for Medical Action Evaluation","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.19004","title":"MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2602.20792","title":"SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking","created":"2026-02-24","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":"2604.09473","title":"Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.04524","title":"High-Fidelity Single-Image Head Modeling with Industry-Grade Topology","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.18102","title":"DanceHMR: Hand-Aware Whole-Body Human Mesh Recovery from Monocular Videos","created":"2026-05-18","cited_by_count":1,"area":null}],"next_cursor":"100"}