{"total":168,"rows":[{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206,"area":null},{"id":"2401.00374","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","created":"2023-12-31","cited_by_count":105,"area":null},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78,"area":null},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64,"area":null},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63,"area":null},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37,"area":null},{"id":"2409.15904","title":"Unimotion: Unifying 3D Human Motion Synthesis and Understanding","created":"2024-09-24","cited_by_count":30,"area":null},{"id":"2312.03703","title":"Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning","created":"2023-12-06","cited_by_count":27,"area":null},{"id":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2401.00889","title":"3D Human Pose Perception from Egocentric Stereo Videos","created":"2023-12-30","cited_by_count":23,"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":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"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":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"area":null},{"id":"2504.19189","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation","created":"2025-04-27","cited_by_count":17,"area":null},{"id":"2411.19824","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","created":"2024-11-29","cited_by_count":16,"area":null},{"id":"2412.09220","title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","created":"2024-12-12","cited_by_count":16,"area":null},{"id":"2311.12028","title":"Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation","created":"2023-11-20","cited_by_count":15,"area":null},{"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":"2506.03481","title":"Heterogeneous Skeleton-Based Action Representation Learning","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2403.10082","title":"CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner","created":"2024-03-15","cited_by_count":11,"area":null},{"id":"2411.18808","title":"Lifting Motion to the 3D World via 2D Diffusion","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2508.12586","title":"Foundation Model for Skeleton-Based Human Action Understanding","created":"2025-08-18","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":"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":"2505.13437","title":"FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance","created":"2025-05-19","cited_by_count":9,"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":"2505.09379","title":"Text-driven Motion Generation: Overview, Challenges and Directions","created":"2025-05-14","cited_by_count":8,"area":null},{"id":"2507.05419","title":"Motion Generation: A Survey of Generative Approaches and Benchmarks","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2412.18883","title":"MotionMap: Representing Multimodality in Human Pose Forecasting","created":"2024-12-25","cited_by_count":7,"area":null},{"id":"2503.11652","title":"Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation","created":"2025-03-14","cited_by_count":7,"area":null},{"id":"2504.09862","title":"RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence","created":"2025-04-14","cited_by_count":7,"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":"2404.14634","title":"UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues","created":"2024-04-23","cited_by_count":6,"area":null},{"id":"2405.17817","title":"Benchmarking Skeleton-based Motion Encoder Models for Clinical Applications: Estimating Parkinson's Disease Severity in Walking Sequences","created":"2024-05-28","cited_by_count":6,"area":null},{"id":"2410.07795","title":"Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos","created":"2024-10-10","cited_by_count":6,"area":null},{"id":"2504.03006","title":"DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2510.04312","title":"CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessment","created":"2025-10-05","cited_by_count":6,"area":null},{"id":"2406.02978","title":"Self-Supervised Skeleton-Based Action Representation Learning: A Benchmark and Beyond","created":"2024-06-05","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":"2509.06956","title":"H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2403.09407","title":"LM2D: Lyrics- and Music-Driven Dance Synthesis","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2404.15719","title":"HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2407.16341","title":"Motion Capture from Inertial and Vision Sensors","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2508.08179","title":"PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2510.10868","title":"FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2601.21904","title":"Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2403.06164","title":"Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation","created":"2024-03-10","cited_by_count":3,"area":null},{"id":"2407.10099","title":"STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video","created":"2024-07-14","cited_by_count":3,"area":null},{"id":"2407.10935","title":"STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2408.06614","title":"ViMo: Generating Motions from Casual Videos","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2410.07153","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2412.05277","title":"Text to Blind Motion","created":"2024-12-06","cited_by_count":3,"area":null},{"id":"2412.19676","title":"Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation","created":"2024-12-27","cited_by_count":3,"area":null},{"id":"2502.12546","title":"Spatiotemporal Multi-Camera Calibration using Freely Moving People","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2507.20170","title":"PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Tasks","created":"2025-07-27","cited_by_count":3,"area":null},{"id":"2508.10897","title":"Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2601.19580","title":"QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2603.29692","title":"SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition","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":"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":"2401.00921","title":"Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2402.18196","title":"NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2404.12625","title":"SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers","created":"2024-04-19","cited_by_count":2,"area":null},{"id":"2407.09694","title":"Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images","created":"2024-07-12","cited_by_count":2,"area":null},{"id":"2409.01879","title":"SPiKE: 3D Human Pose from Point Cloud Sequences","created":"2024-09-03","cited_by_count":2,"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":"2502.21085","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":"2503.00071","title":"I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialogue","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2505.10888","title":"PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networks","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.06139","title":"DiffCap: Diffusion-based Real-time Human Motion Capture using Sparse IMUs and a Monocular Camera","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2508.10522","title":"EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2509.07994","title":"STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2511.09502","title":"DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimation","created":"2025-11-12","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":"2604.03652","title":"Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimation","created":"2026-04-04","cited_by_count":2,"area":null},{"id":"2604.09715","title":"MuPPet: Multi-person 2D-to-3D Pose Lifting","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2406.19726","title":"EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2412.10458","title":"Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2505.21309","title":"Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.09672","title":"VST-Pose: A Velocity-Integrated Spatiotem-poral Attention Network for Human WiFi Pose Estimation","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2508.02056","title":"StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.07112","title":"AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Lifting","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2509.10096","title":"HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.21136","title":"Embodied Representation Alignment with Mirror Neurons","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.16949","title":"MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2512.21054","title":"DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2512.21064","title":"Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition","created":"2025-12-24","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":"2601.16079","title":"Masked Modeling for Human Motion Recovery Under Occlusions","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2602.02401","title":"Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation","created":"2026-02-02","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":"2603.25283","title":"A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.05390","title":"LAMP: Localization Aware Multi-camera People Tracking in Metric 3D World","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2608.00371","title":"Decoding Children's Gait Behavior","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2608.20587","title":"Aggregate, Don't Adapt: Subject-Level Posterior Aggregation and Transductive Calibration for Cross-Site Parkinsonian Gait Severity","created":"2026-08-20","cited_by_count":1,"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":"2311.12421","title":"Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency","created":"2023-11-21","cited_by_count":0,"area":null}],"next_cursor":"100"}