{"list":"other","total":97,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"id":"2507.12440","title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","created":"2025-07-16","cited_by_count":128},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2104.14639","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","created":"2021-04-29","cited_by_count":123},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"2402.14654","title":"Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot","created":"2024-02-22","cited_by_count":101},{"id":"2212.04636","title":"Ego-Body Pose Estimation via Ego-Head Pose Estimation","created":"2022-12-09","cited_by_count":94},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2509.00576","title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model","created":"2025-08-30","cited_by_count":92},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82},{"id":"2212.10621","title":"Full-Body Articulated Human-Object Interaction","created":"2022-12-20","cited_by_count":78},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78},{"id":"2511.17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","created":"2025-11-21","cited_by_count":78},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65},{"id":"2603.03596","title":"MEM: Multi-Scale Embodied Memory for Vision Language Action Models","created":"2026-03-04","cited_by_count":61},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2401.10232","title":"ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions","created":"2024-01-18","cited_by_count":57},{"id":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51},{"id":"2512.22414","title":"Emergence of Human to Robot Transfer in Vision-Language-Action Models","created":"2025-12-27","cited_by_count":42},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37},{"id":"2407.12371","title":"HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects","created":"2024-07-17","cited_by_count":36},{"id":"2512.11047","title":"WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control","created":"2025-12-11","cited_by_count":36},{"id":"2602.22010","title":"World Guidance: World Modeling in Condition Space for Action Generation","created":"2026-02-25","cited_by_count":36},{"id":"2312.06583","title":"3D Hand Pose Estimation in Everyday Egocentric Images","created":"2023-12-11","cited_by_count":34},{"id":"2601.22153","title":"DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation","created":"2026-01-29","cited_by_count":34},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32},{"id":"2512.24653","title":"RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence","created":"2025-12-31","cited_by_count":32},{"id":"2412.17806","title":"Reconstructing People, Places, and Cameras","created":"2024-12-23","cited_by_count":31},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2501.02158","title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild","created":"2025-01-04","cited_by_count":29},{"id":"2509.19626","title":"EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data","created":"2025-09-23","cited_by_count":29},{"id":"2511.15704","title":"In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data","created":"2025-11-19","cited_by_count":26},{"id":"2410.07164","title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation","created":"2024-10-09","cited_by_count":25},{"id":"2203.10385","title":"PressureVision: Estimating Hand Pressure from a Single RGB Image","created":"2022-03-19","cited_by_count":23},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21},{"id":"2509.04443","title":"EMMA: Scaling Mobile Manipulation via Egocentric Human Data","created":"2025-09-04","cited_by_count":21},{"id":"2603.03243","title":"HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations","created":"2026-03-03","cited_by_count":16},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14},{"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},{"id":"2503.21313","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","created":"2025-03-27","cited_by_count":11},{"id":"2601.01222","title":"UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass","created":"2026-01-03","cited_by_count":9},{"id":"2605.13083","title":"TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video","created":"2026-05-13","cited_by_count":7},{"id":"2403.12434","title":"Human Mesh Recovery from Arbitrary Multi-view Images","created":"2024-03-19","cited_by_count":6},{"id":"2603.19227","title":"Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer","created":"2026-03-19","cited_by_count":4},{"id":"2606.09243","title":"EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video","created":"2026-06-08","cited_by_count":4},{"id":"2603.15612","title":"HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions","created":"2026-03-16","cited_by_count":2},{"id":"2606.14841","title":"Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking","created":"2026-06-12","cited_by_count":2},{"id":"2603.13375","title":"InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization","created":"2026-03-10","cited_by_count":1}],"next_cursor":null}