{"total":87,"rows":[{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116,"area":null},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114,"area":null},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94,"area":null},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65,"area":null},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2401.08570","title":"RoHM: Robust Human Motion Reconstruction via Diffusion","created":"2024-01-16","cited_by_count":48,"area":null},{"id":"2304.11118","title":"BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis","created":"2023-04-21","cited_by_count":45,"area":null},{"id":"2309.09294","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","created":"2023-09-17","cited_by_count":40,"area":null},{"id":"2308.06493","title":"EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere","created":"2023-08-12","cited_by_count":34,"area":null},{"id":"2403.06365","title":"Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style","created":"2024-03-11","cited_by_count":33,"area":null},{"id":"2308.16682","title":"DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion","created":"2023-08-31","cited_by_count":31,"area":null},{"id":"2311.16495","title":"Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement","created":"2023-11-28","cited_by_count":31,"area":null},{"id":"2401.00847","title":"Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera","created":"2024-01-01","cited_by_count":31,"area":null},{"id":"2409.13426","title":"HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device","created":"2024-09-20","cited_by_count":27,"area":null},{"id":"2403.03561","title":"HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations","created":"2024-03-06","cited_by_count":25,"area":null},{"id":"2405.20786","title":"Stratified Avatar Generation from Sparse Observations","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2508.02106","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis","created":"2025-08-04","cited_by_count":20,"area":null},{"id":"2404.19541","title":"Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging","created":"2024-04-30","cited_by_count":18,"area":null},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17,"area":null},{"id":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17,"area":null},{"id":"2404.04890","title":"A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2408.07295","title":"Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots","created":"2024-07-30","cited_by_count":16,"area":null},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2408.17168","title":"EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs","created":"2024-08-30","cited_by_count":13,"area":null},{"id":"2401.13699","title":"Generative AI-Driven Human Digital Twin in IoT-Healthcare: A Comprehensive Survey","created":"2024-01-22","cited_by_count":11,"area":null},{"id":"2402.09211","title":"DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced Three-Point Trackers","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2412.02903","title":"EgoCast: Forecasting Egocentric Human Pose in the Wild","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2412.10235","title":"EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling","created":"2024-12-13","cited_by_count":11,"area":null},{"id":"2504.05265","title":"From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models","created":"2025-04-07","cited_by_count":11,"area":null},{"id":"2409.00343","title":"EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System","created":"2024-08-31","cited_by_count":9,"area":null},{"id":"2403.17893","title":"A Survey on 3D Egocentric Human Pose Estimation","created":"2024-03-26","cited_by_count":8,"area":null},{"id":"2508.04681","title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","created":"2025-08-06","cited_by_count":8,"area":null},{"id":"2506.10580","title":"Transformer IMU Calibrator: Dynamic On-body IMU Calibration for Inertial Motion Capture","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2502.05641","title":"Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2502.07869","title":"EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2503.14919","title":"GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2311.12804","title":"Towards the generation of synchronized and believable non-verbal facial behaviors of a talking virtual agent","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2503.23094","title":"FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2508.21556","title":"ECHO: Ego-Centric modeling of Human-Object interactions","created":"2025-08-29","cited_by_count":5,"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":"2505.05336","title":"Progressive Inertial Poser: Progressive Real-Time Kinematic Chain Estimation for 3D Full-Body Pose from Three IMU Sensors","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2403.14104","title":"Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2406.14567","title":"DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2411.18377","title":"XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2505.10810","title":"MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.11334","title":"MARRS: Masked Autoregressive Unit-based Reaction Synthesis","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":"2603.04090","title":"EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.16233","title":"Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2401.11783","title":"Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2404.11554","title":"Predicting Long-horizon Futures by Conditioning on Geometry and Time","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2504.18332","title":"SSD-Poser: Avatar Pose Estimation with State Space Duality from Sparse Observations","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2506.17505","title":"Learning golf swing signatures from a single wrist-worn inertial sensor","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2510.17101","title":"Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.16791","title":"KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2605.05680","title":"MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.18243","title":"MOCHI: Motion Enhancement of Collaborative Human-object Interactions","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.26741","title":"PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.09780","title":"Towards Real-World Wearable Motion Reconstruction","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.15868","title":"EgoExoMoCap: Distributed Ego-Exo Human Motion Capture","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2409.14101","title":"PoseAugment: Generative Human Pose Data Augmentation with Physical Plausibility for IMU-based Motion Capture","created":"2024-09-21","cited_by_count":0,"area":null},{"id":"2505.01802","title":"Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows","created":"2025-05-03","cited_by_count":0,"area":null},{"id":"2505.06411","title":"MAGE:A Multi-stage Avatar Generator with Sparse Observations","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2506.01757","title":"Efficient Egocentric Action Recognition with Multimodal Data","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.02722","title":"MoGIC: Boosting Motion Generation via Intention Understanding and Visual Context","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.22712","title":"Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2511.16264","title":"Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.19283","title":"OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2601.01360","title":"Garment Inertial Denoiser (GID): Endowing Accurate Motion Capture via Loose IMU Denoiser","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2601.02096","title":"Dancing Points: Synthesizing Ballroom Dancing with Three-Point Inputs","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.19519","title":"Mocap Anywhere: Towards Pairwise-Distance based Motion Capture in the Wild (for the Wild)","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.05590","title":"EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.18319","title":"Robo-Saber: Generating and Simulating Virtual Reality Players","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.22631","title":"AtomicMotion: Learning Human Motion From Different Human Parts","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.23000","title":"MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations","created":"2026-06-22","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":"2607.27755","title":"EgoGVAE: Ego-body Mesh Reconstruction via Guided Variational Autoencoder","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.20312","title":"Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis","created":"2026-08-20","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":"2610.16277","title":"FlowAvatar: Real-Time Full-Body Avatars from Sparse Egocentric Inputs on Consumer XR Devices","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18871","title":"Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18872","title":"EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}