{"total":111,"rows":[{"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":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206,"area":"offlinerl"},{"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":"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":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137,"area":null},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124,"area":"deeprl"},{"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":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"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":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78,"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":"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":"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":"2108.07044","title":"Towards unconstrained joint hand-object reconstruction from RGB videos","created":"2021-08-16","cited_by_count":58,"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":"2312.00775","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","created":"2023-12-01","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":"2109.11399","title":"A Skeleton-Driven Neural Occupancy Representation for Articulated Hands","created":"2021-09-23","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":"2304.11970","title":"gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction","created":"2023-04-24","cited_by_count":50,"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":"2107.00434","title":"Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation","created":"2021-07-01","cited_by_count":40,"area":null},{"id":"2207.11061","title":"3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal","created":"2022-07-22","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":"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":"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":"2107.11646","title":"Hand Image Understanding via Deep Multi-Task Learning","created":"2021-07-24","cited_by_count":31,"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":"2302.14348","title":"Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes","created":"2023-02-28","cited_by_count":26,"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":"2211.15692","title":"H3WB: Human3.6M 3D WholeBody Dataset and Benchmark","created":"2022-11-28","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":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20,"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":"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":"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":"2508.05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips","created":"2025-08-07","cited_by_count":17,"area":"diffusion"},{"id":"2102.09244","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","created":"2021-02-18","cited_by_count":15,"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},{"id":"2310.11696","title":"MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision","created":"2023-10-18","cited_by_count":12,"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":"2203.15865","title":"On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2501.11992","title":"Survey on Hand Gesture Recognition from Visual Input","created":"2025-01-21","cited_by_count":10,"area":null},{"id":"2504.09097","title":"BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting","created":"2025-04-12","cited_by_count":10,"area":null},{"id":"2101.09745","title":"Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views","created":"2021-01-24","cited_by_count":9,"area":null},{"id":"2412.01537","title":"HandOS: 3D Hand Reconstruction in One Stage","created":"2024-12-02","cited_by_count":9,"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":"2302.02410","title":"Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2106.05954","title":"Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2206.07117","title":"TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimation","created":"2022-06-14","cited_by_count":7,"area":null},{"id":"2302.00988","title":"HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2407.15844","title":"HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning","created":"2024-07-22","cited_by_count":7,"area":null},{"id":"2109.11747","title":"Multi-View Video-Based 3D Hand Pose Estimation","created":"2021-09-24","cited_by_count":6,"area":null},{"id":"2112.06389","title":"Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation","created":"2021-12-13","cited_by_count":6,"area":null},{"id":"2305.04328","title":"Neural Voting Field for Camera-Space 3D Hand Pose Estimation","created":"2023-05-07","cited_by_count":6,"area":null},{"id":"2503.13303","title":"UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation","created":"2025-03-17","cited_by_count":6,"area":null},{"id":"2101.11239","title":"Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image","created":"2021-01-27","cited_by_count":5,"area":null},{"id":"2109.13879","title":"3D Hand Pose and Shape Estimation from RGB Images for Keypoint-Based Hand Gesture Recognition","created":"2021-09-28","cited_by_count":5,"area":null},{"id":"2202.11891","title":"HMD-EgoPose: Head-Mounted Display-Based Egocentric Marker-Less Tool and Hand Pose Estimation for Augmented Surgical Guidance","created":"2022-02-24","cited_by_count":5,"area":null},{"id":"2309.16140","title":"CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Prompting","created":"2023-09-28","cited_by_count":5,"area":null},{"id":"2503.23094","title":"FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2111.08468","title":"Point detection through multi-instance deep heatmap regression for sutures in endoscopy","created":"2021-11-16","cited_by_count":4,"area":null},{"id":"2505.07012","title":"Hand-Shadow Poser","created":"2025-05-11","cited_by_count":4,"area":null},{"id":"2103.02852","title":"Data Augmentation for Object Detection via Differentiable Neural Rendering","created":"2021-03-04","cited_by_count":3,"area":null},{"id":"2111.06500","title":"Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation","created":"2021-11-11","cited_by_count":3,"area":null},{"id":"2301.10431","title":"Bias-Compensated Integral Regression for Human Pose Estimation","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2311.14189","title":"D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction","created":"2023-11-23","cited_by_count":3,"area":null},{"id":"2311.17366","title":"Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling","created":"2023-11-29","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":"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":"2105.09880","title":"DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2105.10902","title":"A hybrid classification-regression approach for 3D hand pose estimation using graph convolutional networks","created":"2021-05-23","cited_by_count":2,"area":null},{"id":"2106.05953","title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2107.05509","title":"Multi-view Image-based Hand Geometry Refinement using Differentiable Monte Carlo Ray Tracing","created":"2021-07-12","cited_by_count":2,"area":null},{"id":"2308.10146","title":"OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2402.01389","title":"SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-View Adaptation","created":"2024-02-02","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":"2606.30598","title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2102.07067","title":"Fast Monocular Hand Pose Estimation on Embedded Systems","created":"2021-02-14","cited_by_count":1,"area":null},{"id":"2105.10904","title":"Skeleton-aware multi-scale heatmap regression for 2D hand pose estimation","created":"2021-05-23","cited_by_count":1,"area":null},{"id":"2111.15199","title":"Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2206.00171","title":"Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2303.15147","title":"Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2306.12652","title":"UltraGlove: Hand Pose Estimation with Mems-Ultrasonic Sensors","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2308.04074","title":"Exploiting Spatial-Temporal Context for Interacting Hand Reconstruction on Monocular RGB Video","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2509.13883","title":"EvHand-FPV: Efficient Event-Based 3D Hand Tracking from First-Person View","created":"2025-09-17","cited_by_count":1,"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":"2607.16192","title":"MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2104.12123","title":"Parallel mesh reconstruction streams for pose estimation of interacting hands","created":"2021-04-25","cited_by_count":0,"area":null},{"id":"2303.14838","title":"Lightweight Estimation of Hand Mesh and Biomechanically Feasible Kinematic Parameters","created":"2023-03-26","cited_by_count":0,"area":null},{"id":"2310.12189","title":"Mesh Represented Recycle Learning for 3D Hand Pose and Mesh Estimation","created":"2023-10-18","cited_by_count":0,"area":null}],"next_cursor":"100"}