{"total":230,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327,"area":null},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325,"area":null},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"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":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167,"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":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141,"area":null},{"id":"2104.07267","title":"ContactOpt: Optimizing Contact to Improve Grasps","created":"2021-04-15","cited_by_count":139,"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":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129,"area":null},{"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,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110,"area":"diffusion"},{"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":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2204.07153","title":"What's in your hands? 3D Reconstruction of Generic Objects in Hands","created":"2022-04-14","cited_by_count":90,"area":null},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88,"area":null},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82,"area":null},{"id":"2109.05488","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","created":"2021-09-12","cited_by_count":76,"area":null},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74,"area":null},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74,"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":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2108.07044","title":"Towards unconstrained joint hand-object reconstruction from RGB videos","created":"2021-08-16","cited_by_count":58,"area":null},{"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,"area":null},{"id":"2204.13062","title":"Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution","created":"2022-04-27","cited_by_count":54,"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":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51,"area":null},{"id":"2412.12861","title":"Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera","created":"2024-12-17","cited_by_count":51,"area":null},{"id":"2109.11399","title":"A Skeleton-Driven Neural Occupancy Representation for Articulated Hands","created":"2021-09-23","cited_by_count":50,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2211.00099","title":"UmeTrack: Unified multi-view end-to-end hand tracking for VR","created":"2022-10-31","cited_by_count":50,"area":null},{"id":"2309.08942","title":"AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose","created":"2023-09-16","cited_by_count":49,"area":null},{"id":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48,"area":null},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46,"area":null},{"id":"2404.12383","title":"G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis","created":"2024-04-18","cited_by_count":43,"area":"diffusion"},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40,"area":null},{"id":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36,"area":null},{"id":"2411.14280","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild","created":"2024-11-21","cited_by_count":36,"area":null},{"id":"2209.09484","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","created":"2022-09-20","cited_by_count":35,"area":null},{"id":"2310.17768","title":"A Dataset of Relighted 3D Interacting Hands","created":"2023-10-26","cited_by_count":35,"area":null},{"id":"2403.16428","title":"Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects","created":"2024-03-25","cited_by_count":35,"area":null},{"id":"2106.04324","title":"Contrastive Representation Learning for Hand Shape Estimation","created":"2021-06-08","cited_by_count":34,"area":null},{"id":"2303.17592","title":"Learning Human-to-Robot Handovers from Point Clouds","created":"2023-03-30","cited_by_count":34,"area":null},{"id":"2312.06583","title":"3D Hand Pose Estimation in Everyday Egocentric Images","created":"2023-12-11","cited_by_count":34,"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":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31,"area":null},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31,"area":null},{"id":"2404.03590","title":"SemGrasp: Semantic Grasp Generation via Language Aligned Discretization","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","cited_by_count":29,"area":null},{"id":"2201.09548","title":"Consistent 3D Hand Reconstruction in Video via self-supervised Learning","created":"2022-01-24","cited_by_count":28,"area":null},{"id":"2212.09530","title":"HARP: Personalized Hand Reconstruction from a Monocular RGB Video","created":"2022-12-19","cited_by_count":28,"area":null},{"id":"2403.17422","title":"InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion","created":"2024-03-26","cited_by_count":28,"area":"diffusion"},{"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":"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":"2309.01909","title":"A Survey on Physics Informed Reinforcement Learning: Review and Open Problems","created":"2023-09-05","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":"2201.10145","title":"Riemannian Local Mechanism for SPD Neural Networks","created":"2022-01-25","cited_by_count":22,"area":null},{"id":"2209.14284","title":"DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2206.12612","title":"Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions","created":"2022-06-25","cited_by_count":21,"area":null},{"id":"2310.10013","title":"Riemannian Residual Neural Networks","created":"2023-10-16","cited_by_count":21,"area":null},{"id":"2409.09300","title":"ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion","created":"2024-09-14","cited_by_count":21,"area":"diffusion"},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21,"area":null},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","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":"2409.02224","title":"EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision","created":"2024-09-03","cited_by_count":19,"area":null},{"id":"2305.04560","title":"Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach","created":"2023-05-08","cited_by_count":18,"area":null},{"id":"2409.02638","title":"MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos","created":"2024-09-04","cited_by_count":18,"area":"diffusion"},{"id":"2110.07692","title":"Shaping embodied agent behavior with activity-context priors from egocentric video","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2206.02257","title":"Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey","created":"2022-06-05","cited_by_count":17,"area":null},{"id":"2209.00489","title":"TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning","created":"2022-09-01","cited_by_count":17,"area":null},{"id":"2209.12009","title":"Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild","created":"2022-09-24","cited_by_count":17,"area":null},{"id":"2308.08231","title":"DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field","created":"2023-08-16","cited_by_count":17,"area":null},{"id":"2312.14157","title":"3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2104.11466","title":"H2O: A Benchmark for Visual Human-human Object Handover Analysis","created":"2021-04-23","cited_by_count":16,"area":null},{"id":"2210.13853","title":"THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2308.11198","title":"Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views","created":"2023-08-22","cited_by_count":16,"area":null},{"id":"2309.09301","title":"RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation","created":"2023-09-17","cited_by_count":16,"area":null},{"id":"2309.10748","title":"SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction","created":"2023-09-19","cited_by_count":16,"area":null},{"id":"2504.08654","title":"The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation","created":"2025-04-11","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":"2412.13187","title":"HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction","created":"2024-12-17","cited_by_count":15,"area":"mllm"},{"id":"2203.08344","title":"Domain Adaptive Hand Keypoint and Pixel Localization in the Wild","created":"2022-03-16","cited_by_count":14,"area":"distill"},{"id":"2307.10387","title":"POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical Activities","created":"2023-07-19","cited_by_count":14,"area":null},{"id":"2303.15477","title":"Adaptive Log-Euclidean Metrics for SPD Matrix Learning","created":"2023-03-26","cited_by_count":13,"area":null},{"id":"2311.05599","title":"SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers","created":"2023-11-09","cited_by_count":13,"area":null},{"id":"2312.04867","title":"HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models","created":"2023-12-08","cited_by_count":13,"area":"diffusion"},{"id":"2405.19206","title":"Matrix Manifold Neural Networks++","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2512.13080","title":"Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos","created":"2025-12-15","cited_by_count":13,"area":"vla"},{"id":"2301.07652","title":"HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects","created":"2023-01-18","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}],"next_cursor":"100"}