{"total":147,"rows":[{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206,"area":"offlinerl"},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182,"area":null},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180,"area":null},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161,"area":null},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160,"area":null},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139,"area":null},{"id":"2210.02697","title":"DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation","created":"2022-10-06","cited_by_count":137,"area":null},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135,"area":null},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131,"area":null},{"id":"2303.00938","title":"UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy","created":"2023-03-02","cited_by_count":124,"area":null},{"id":"2112.03028","title":"D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions","created":"2021-12-01","cited_by_count":113,"area":null},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101,"area":null},{"id":"2311.16098","title":"On Bringing Robots Home","created":"2023-11-27","cited_by_count":101,"area":null},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99,"area":null},{"id":"2204.02445","title":"CHORE: Contact, Human and Object REconstruction from a single RGB image","created":"2022-04-05","cited_by_count":95,"area":null},{"id":"2112.10103","title":"SAGA: Stochastic Whole-Body Grasping with Contact","created":"2021-12-19","cited_by_count":91,"area":null},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89,"area":null},{"id":"2404.00562","title":"Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction","created":"2024-03-31","cited_by_count":86,"area":null},{"id":"2202.10448","title":"Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube","created":"2022-02-21","cited_by_count":82,"area":null},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70,"area":null},{"id":"2303.04805","title":"X-Avatar: Expressive Human Avatars","created":"2023-03-08","cited_by_count":66,"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":"2109.05668","title":"UMPNet: Universal Manipulation Policy Network for Articulated Objects","created":"2021-09-13","cited_by_count":65,"area":null},{"id":"2403.17827","title":"DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions","created":"2024-03-26","cited_by_count":62,"area":"diffusion"},{"id":"2108.07044","title":"Towards unconstrained joint hand-object reconstruction from RGB videos","created":"2021-08-16","cited_by_count":58,"area":null},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58,"area":null},{"id":"2210.00722","title":"GenDexGrasp: Generalizable Dexterous Grasping","created":"2022-10-03","cited_by_count":56,"area":null},{"id":"2309.03891","title":"ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation","created":"2023-09-07","cited_by_count":55,"area":null},{"id":"2310.03740","title":"ContactGen: Generative Contact Modeling for Grasp Generation","created":"2023-10-05","cited_by_count":53,"area":null},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52,"area":null},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2109.11399","title":"A Skeleton-Driven Neural Occupancy Representation for Articulated Hands","created":"2021-09-23","cited_by_count":50,"area":null},{"id":"2111.03062","title":"Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning","created":"2021-11-04","cited_by_count":50,"area":null},{"id":"2211.11903","title":"FLEX: Full-Body Grasping Without Full-Body Grasps","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2302.01295","title":"Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception","created":"2023-02-02","cited_by_count":41,"area":null},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39,"area":null},{"id":"2312.07063","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","created":"2023-12-12","cited_by_count":38,"area":"diffusion"},{"id":"2306.00777","title":"Object pop-up: Can we infer 3D objects and their poses from human interactions alone?","created":"2023-06-01","cited_by_count":37,"area":null},{"id":"2407.12371","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33,"area":null},{"id":"2401.12978","title":"Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models","created":"2024-01-23","cited_by_count":32,"area":"diffusion"},{"id":"2506.09982","title":"AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation","created":"2025-06-11","cited_by_count":32,"area":null},{"id":"2311.16917","title":"UGG: Unified Generative Grasping","created":"2023-11-28","cited_by_count":30,"area":null},{"id":"2412.05066","title":"BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects","created":"2024-12-06","cited_by_count":30,"area":null},{"id":"2209.11221","title":"Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2210.03954","title":"Contact-aware Human Motion Forecasting","created":"2022-10-08","cited_by_count":27,"area":null},{"id":"2308.11617","title":"GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency","created":"2023-08-22","cited_by_count":27,"area":null},{"id":"2205.15608","title":"Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction","created":"2022-05-31","cited_by_count":26,"area":null},{"id":"2312.02137","title":"MANUS: Markerless Grasp Capture using Articulated 3D Gaussians","created":"2023-12-04","cited_by_count":26,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2506.17198","title":"Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation","created":"2025-06-20","cited_by_count":24,"area":null},{"id":"2203.10385","title":"PressureVision: Estimating Hand Pressure from a Single RGB Image","created":"2022-03-19","cited_by_count":23,"area":null},{"id":"2504.17695","title":"PICO: Reconstructing 3D People In Contact with Objects","created":"2025-04-24","cited_by_count":22,"area":null},{"id":"2210.09245","title":"Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraint","created":"2022-10-17","cited_by_count":21,"area":null},{"id":"2405.07391","title":"AnyRotate: Gravity-Invariant In-Hand Object Rotation with Sim-to-Real Touch","created":"2024-05-12","cited_by_count":21,"area":null},{"id":"2412.06334","title":"TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions","created":"2024-12-09","cited_by_count":20,"area":null},{"id":"2308.12288","title":"CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images","created":"2023-08-23","cited_by_count":19,"area":null},{"id":"2408.07147","title":"Controlling the World by Sleight of Hand","created":"2024-08-13","cited_by_count":19,"area":null},{"id":"2310.15599","title":"Grasp Multiple Objects with One Hand","created":"2023-10-24","cited_by_count":18,"area":null},{"id":"2307.03716","title":"SAR: Generalization of Physiological Agility and Dexterity via Synergistic Action Representation","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2307.16897","title":"DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2305.01618","title":"ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation","created":"2023-05-02","cited_by_count":16,"area":null},{"id":"2409.04033","title":"Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics","created":"2024-09-06","cited_by_count":15,"area":null},{"id":"2305.17783","title":"Visual Affordance Prediction for Guiding Robot Exploration","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2308.01854","title":"Reconstructing Three-Dimensional Models of Interacting Humans","created":"2023-08-03","cited_by_count":14,"area":null},{"id":"2412.20104","title":"SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis","created":"2024-12-28","cited_by_count":14,"area":null},{"id":"2505.11152","title":"Learning Dense Hand Contact Estimation from Imbalanced Data","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2305.11427","title":"RGB-D And Thermal Sensor Fusion: A Systematic Literature Review","created":"2023-05-19","cited_by_count":13,"area":null},{"id":"2312.14929","title":"MACS: Mass Conditioned 3D Hand and Object Motion Synthesis","created":"2023-12-22","cited_by_count":13,"area":null},{"id":"2407.15337","title":"ThermalNeRF: Thermal Radiance Fields","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2203.11544","title":"Visuo-Haptic Object Perception for Robots: An Overview","created":"2022-03-22","cited_by_count":12,"area":null},{"id":"2305.03036","title":"3D Reconstruction of Objects in Hands without Real World 3D Supervision","created":"2023-05-04","cited_by_count":12,"area":null},{"id":"2309.03130","title":"MyoDex: A Generalizable Prior for Dexterous Manipulation","created":"2023-09-06","cited_by_count":11,"area":null},{"id":"2404.01727","title":"Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge","created":"2024-04-02","cited_by_count":11,"area":null},{"id":"2505.05517","title":"Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2305.01652","title":"Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection","created":"2023-05-02","cited_by_count":10,"area":null},{"id":"2401.04143","title":"RHOBIN Challenge: Reconstruction of Human Object Interaction","created":"2024-01-07","cited_by_count":10,"area":null},{"id":"2407.12727","title":"NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model","created":"2024-07-17","cited_by_count":10,"area":"diffusion"},{"id":"2407.21510","title":"PEAR: Phrase-Based Hand-Object Interaction Anticipation","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2112.05298","title":"IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes","created":"2021-12-10","cited_by_count":9,"area":null},{"id":"2509.24661","title":"CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representations","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2510.08556","title":"DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2109.04378","title":"Dynamic Modeling of Hand-Object Interactions via Tactile Sensing","created":"2021-09-09","cited_by_count":8,"area":null},{"id":"2205.00848","title":"Stability-driven Contact Reconstruction From Monocular Color Images","created":"2022-05-02","cited_by_count":8,"area":null},{"id":"2208.00874","title":"S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning","created":"2022-08-01","cited_by_count":8,"area":null},{"id":"2304.13651","title":"What Happened 3 Seconds Ago? Inferring the Past with Thermal Imaging","created":"2023-04-26","cited_by_count":8,"area":null},{"id":"2405.11481","title":"Physics-aware Hand-object Interaction Denoising","created":"2024-05-19","cited_by_count":8,"area":null},{"id":"2504.12908","title":"Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation","created":"2025-04-17","cited_by_count":8,"area":null},{"id":"2506.03103","title":"DyTact: Capturing Dynamic Contacts in Hand-Object Manipulation","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2404.15189","title":"Text2Grasp: Grasp synthesis by text prompts of object grasping parts","created":"2024-04-09","cited_by_count":7,"area":null},{"id":"2411.14786","title":"FastGrasp: Efficient Grasp Synthesis with Diffusion","created":"2024-11-22","cited_by_count":7,"area":"diffusion"},{"id":"2408.01953","title":"EqvAfford: SE(3) Equivariance for Point-Level Affordance Learning","created":"2024-08-04","cited_by_count":6,"area":null},{"id":"2408.16770","title":"3D Whole-body Grasp Synthesis with Directional Controllability","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2208.05632","title":"Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactions","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2303.12726","title":"Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum","created":"2023-03-14","cited_by_count":5,"area":null},{"id":"2503.19457","title":"G-DexGrasp: Generalizable Dexterous Grasping Synthesis Via Part-Aware Prior Retrieval and Prior-Assisted Generation","created":"2025-03-25","cited_by_count":5,"area":null},{"id":"2603.05754","title":"Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation","created":"2026-03-05","cited_by_count":5,"area":"vla"}],"next_cursor":"100"}