{"total":250,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"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":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"area":null},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287,"area":null},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265,"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":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"area":null},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2207.06400","title":"PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images","created":"2022-07-13","cited_by_count":153,"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":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"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":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"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":"2212.04498","title":"VideoDex: Learning Dexterity from Internet Videos","created":"2022-12-08","cited_by_count":106,"area":null},{"id":"2103.10429","title":"Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks","created":"2021-03-18","cited_by_count":103,"area":null},{"id":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87,"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":"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":"2207.13820","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","created":"2022-07-27","cited_by_count":81,"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":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70,"area":null},{"id":"2602.15989","title":"SAM 3D Body: Robust Full-Body Human Mesh Recovery","created":"2026-02-17","cited_by_count":69,"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":"2103.11703","title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","created":"2021-03-22","cited_by_count":65,"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":"2204.01695","title":"LISA: Learning Implicit Shape and Appearance of Hands","created":"2022-04-04","cited_by_count":63,"area":null},{"id":"2103.02845","title":"Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration","created":"2021-03-04","cited_by_count":59,"area":null},{"id":"2207.12909","title":"AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction","created":"2022-07-26","cited_by_count":59,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"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":"2310.03740","title":"ContactGen: Generative Contact Modeling for Grasp Generation","created":"2023-10-05","cited_by_count":53,"area":null},{"id":"2102.03725","title":"I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling","created":"2021-02-07","cited_by_count":52,"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":"2304.05690","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","created":"2023-04-12","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":"2303.14747","title":"Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation","created":"2023-03-26","cited_by_count":47,"area":null},{"id":"2109.01723","title":"Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction","created":"2021-09-03","cited_by_count":44,"area":null},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41,"area":null},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39,"area":null},{"id":"2505.07813","title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","created":"2025-05-12","cited_by_count":38,"area":null},{"id":"2303.05938","title":"ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction","created":"2023-03-10","cited_by_count":37,"area":null},{"id":"2207.10387","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","created":"2022-07-21","cited_by_count":36,"area":null},{"id":"2303.13652","title":"Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild","created":"2023-03-23","cited_by_count":36,"area":null},{"id":"2211.16835","title":"Reconstructing Hand-Held Objects from Monocular Video","created":"2022-11-30","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":"2106.04324","title":"Contrastive Representation Learning for Hand Shape Estimation","created":"2021-06-08","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":"2108.10378","title":"Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras","created":"2021-08-23","cited_by_count":33,"area":null},{"id":"2110.09554","title":"TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation","created":"2021-10-18","cited_by_count":32,"area":null},{"id":"2304.14299","title":"A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image","created":"2023-04-27","cited_by_count":32,"area":null},{"id":"2107.11646","title":"Hand Image Understanding via Deep Multi-Task Learning","created":"2021-07-24","cited_by_count":31,"area":null},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","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":"2210.15664","title":"State of the Art in Dense Monocular Non-Rigid 3D Reconstruction","created":"2022-10-27","cited_by_count":30,"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":"2308.13369","title":"Distribution-Aligned Diffusion for Human Mesh Recovery","created":"2023-08-25","cited_by_count":27,"area":null},{"id":"2403.01813","title":"A Simple Baseline for Efficient Hand Mesh Reconstruction","created":"2024-03-04","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":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2210.07650","title":"DART: Articulated Hand Model with Diverse Accessories and Rich Textures","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24,"area":null},{"id":"2106.11725","title":"RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video","created":"2021-06-22","cited_by_count":23,"area":null},{"id":"2208.11547","title":"ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild","created":"2022-08-23","cited_by_count":23,"area":null},{"id":"2211.15692","title":"H3WB: Human3.6M 3D WholeBody Dataset and Benchmark","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2410.11520","title":"Look Ma, no markers: holistic performance capture without the hassle","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2211.08805","title":"Interacting Hand-Object Pose Estimation via Dense Mutual Attention","created":"2022-11-16","cited_by_count":22,"area":null},{"id":"2412.02725","title":"emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21,"area":null},{"id":"2204.00172","title":"A Unified Framework for Domain Adaptive Pose Estimation","created":"2022-04-01","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":"2104.08885","title":"A survey of image labelling for computer vision applications","created":"2021-04-18","cited_by_count":18,"area":null},{"id":"2303.01765","title":"Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement","created":"2023-03-03","cited_by_count":18,"area":null},{"id":"2308.14082","title":"Reconstructing Interacting Hands with Interaction Prior from Monocular Images","created":"2023-08-27","cited_by_count":18,"area":null},{"id":"2110.00119","title":"HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge","created":"2021-09-30","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":"2303.02862","title":"EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervision","created":"2023-03-06","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":"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":"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":"2102.09244","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","created":"2021-02-18","cited_by_count":15,"area":null},{"id":"2308.03202","title":"Source-free Domain Adaptive Human Pose Estimation","created":"2023-08-06","cited_by_count":15,"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":"2106.10893","title":"PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging","created":"2021-06-21","cited_by_count":14,"area":null},{"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":"2402.17062","title":"HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields","created":"2024-02-26","cited_by_count":14,"area":null},{"id":"2403.07346","title":"Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction","created":"2024-03-12","cited_by_count":14,"area":null},{"id":"2502.16533","title":"A Survey of Graph Transformers: Architectures, Theories and Applications","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2403.18575","title":"HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions","created":"2024-03-27","cited_by_count":13,"area":null}],"next_cursor":"100"}