{"total":124,"rows":[{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"area":null},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66,"area":null},{"id":"2601.04061","title":"CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos","created":"2026-01-07","cited_by_count":31,"area":"vla"},{"id":"2411.17799","title":"Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2605.24934","title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","created":"2026-05-24","cited_by_count":16,"area":null},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15,"area":null},{"id":"2602.21736","title":"Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild","created":"2026-02-25","cited_by_count":15,"area":"vla"},{"id":"2510.11649","title":"PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image","created":"2025-10-13","cited_by_count":14,"area":null},{"id":"2503.21313","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2606.17200","title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","created":"2026-06-15","cited_by_count":10,"area":"vla"},{"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":"2508.18213","title":"Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance","created":"2025-08-25","cited_by_count":8,"area":"diffusion"},{"id":"2512.06065","title":"EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing","created":"2025-12-05","cited_by_count":8,"area":null},{"id":"2604.05621","title":"FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos","created":"2026-04-07","cited_by_count":8,"area":null},{"id":"2601.01050","title":"EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos","created":"2026-01-03","cited_by_count":7,"area":"diffusion"},{"id":"2602.06226","title":"ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2602.03796","title":"3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2412.13393","title":"MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2508.01835","title":"Diffusion-based 3D Hand Motion Recovery with Intuitive Physics","created":"2025-08-03","cited_by_count":5,"area":null},{"id":"2508.15902","title":"Text-Driven 3D Hand Motion Generation from Sign Language Data","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2605.31234","title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model","created":"2026-05-29","cited_by_count":5,"area":"vla"},{"id":"2606.11628","title":"LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition","created":"2026-06-10","cited_by_count":5,"area":null},{"id":"2606.30308","title":"The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction","created":"2026-06-29","cited_by_count":5,"area":"diffusion"},{"id":"2503.09871","title":"LuciBot: Automated Robot Policy Learning from Generated Videos","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2510.10793","title":"ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2602.04672","title":"AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation","created":"2026-02-04","cited_by_count":4,"area":"agents"},{"id":"2603.11755","title":"Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints","created":"2026-03-12","cited_by_count":4,"area":"wm"},{"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":"2603.25791","title":"ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2603.26068","title":"PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2512.00960","title":"Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2512.07394","title":"Reconstructing Objects along Hand Interaction Timelines in Egocentric Video","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2601.19850","title":"EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2601.20835","title":"Open-Vocabulary Functional 3D Human-Scene Interaction Generation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2602.01960","title":"Grounding Generated Videos in Feasible Plans via World Models","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"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":"2603.22193","title":"PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2603.23997","title":"HGGT: Robust and Flexible 3D Hand Mesh Reconstruction from Uncalibrated Images","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2605.05712","title":"EgoEMG: A Multimodal Egocentric Dataset with Bilateral EMG and Vision for Hand Pose Estimation","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.05945","title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.12498","title":"EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.20992","title":"Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction","created":"2026-05-20","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":"2510.00506","title":"Affordance-Guided Diffusion Prior for 3D Hand Reconstruction","created":"2025-10-01","cited_by_count":2,"area":"diffusion"},{"id":"2510.05662","title":"DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulation","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2512.00885","title":"HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2602.21631","title":"UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.10446","title":"SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.14726","title":"Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator","created":"2026-03-16","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":"2603.25539","title":"PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2603.25726","title":"AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2604.19624","title":"GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2605.17354","title":"GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.18553","title":"StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video","created":"2026-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2606.06627","title":"What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.10025","title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2606.30598","title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.02075","title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.11221","title":"HandFlow: Fully Generative 4D Hand Recovery with Flow Matching","created":"2026-07-13","cited_by_count":2,"area":"diffusion"},{"id":"2608.06192","title":"HOPE: Hand-Object Pressure Estimation from Monocular Videos","created":"2026-08-06","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":"2608.15060","title":"EgoTac: In-the-wild Tactile Prediction from Egocentric Vision","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2608.20308","title":"ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery","created":"2026-08-20","cited_by_count":2,"area":"diffusion"},{"id":"2609.04958","title":"MINT: A Unified Model for World-Space Camera and Hand Motion Estimation from Scalable Egocentric Pipeline Supervision","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2510.06145","title":"Bimanual 3D Hand Motion and Articulation Forecasting in Everyday Images","created":"2025-10-07","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":"2601.05243","title":"Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2602.03200","title":"Hand3R: Online 4D Hand-Scene Reconstruction in the Wild","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.12533","title":"Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2603.19059","title":"SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"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},{"id":"2606.08056","title":"What's the Point? Spatial Grammar & Index Resolution for Sign Language Processing","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.17384","title":"Improving and Evaluating Hand-Object Interaction Detection","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.28673","title":"BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.10287","title":"InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2607.28394","title":"Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.05215","title":"VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2609.03199","title":"RoboTok: A Scalable Data Engine for Internet Demonstration Video Retrieval and Dexterous Manipulation Learning","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2502.08452","title":"Learning to Push, Group, and Grasp: A Diffusion Policy Approach for Multi-Object Delivery","created":"2025-02-12","cited_by_count":0,"area":"diffusion"},{"id":"2504.08272","title":"Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse Synthesis","created":"2025-04-11","cited_by_count":0,"area":"diffusion"},{"id":"2510.00527","title":"Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation","created":"2025-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2511.12030","title":"VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2511.14945","title":"Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.16727","title":"OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.05844","title":"DexterCap: An Affordable and Automated System for Capturing Dexterous Hand-Object Manipulation","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2603.11383","title":"Vision-Based Hand Shadowing for Robotic Manipulation via Inverse Kinematics","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.16444","title":"Fast-HaMeR: Boosting Hand Mesh Reconstruction using Knowledge Distillation","created":"2026-03-17","cited_by_count":0,"area":"distill"},{"id":"2603.17396","title":"Gesture-Aware Pretraining and Token Fusion for 3D Hand Pose Estimation","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.08943","title":"MASS: Mesh-inellipse Aligned Deformable Surfel Splatting for Hand Reconstruction and Rendering from Egocentric Monocular Video","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.05367","title":"Tamaththul3D: High-Fidelity 3D Saudi Sign Language Avatars from Monocular Video","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.17638","title":"TouchMap-OR: Multi-View 3D Mapping of Hand-Surface Contacts","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.17742","title":"UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.22231","title":"REACH: Hand Pose Estimation from Room Corners","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.23523","title":"ComPose: When to Trust Hands for Object Pose Tracking","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.23653","title":"ExpOS: Explainable Open-Surgery Skills Assessment Using 3D Hand Reconstruction","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.30671","title":"WristCompass: Kinematic Coupling as a Learnable Visual Concept for Ego-Camera Orientation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.16436","title":"V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.17427","title":"Impact of Hand Impairment and Occlusions on Hand Pose Estimation Accuracy in Augmented Reality Applications","created":"2026-06-16","cited_by_count":0,"area":null}],"next_cursor":"100"}