{"total":82,"rows":[{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312,"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":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87,"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":"2106.08059","title":"Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera","created":"2021-06-15","cited_by_count":70,"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":"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":"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":"2103.15706","title":"StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval","created":"2021-03-29","cited_by_count":50,"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":"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":"2303.05938","title":"ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction","created":"2023-03-10","cited_by_count":37,"area":null},{"id":"2207.11061","title":"3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal","created":"2022-07-22","cited_by_count":36,"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":"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":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","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":"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":"2312.16737","title":"HMP: Hand Motion Priors for Pose and Shape Estimation from Video","created":"2023-12-27","cited_by_count":23,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","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":"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":"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":"2102.09244","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","created":"2021-02-18","cited_by_count":15,"area":null},{"id":"2304.03635","title":"A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2023-04-07","cited_by_count":15,"area":null},{"id":"2102.03424","title":"Learning Audio-Visual Correlations from Variational Cross-Modal Generation","created":"2021-02-05","cited_by_count":14,"area":null},{"id":"2103.17104","title":"Deep Image Harmonization by Bridging the Reality Gap","created":"2021-03-31","cited_by_count":11,"area":null},{"id":"2303.15417","title":"Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding","created":"2023-03-27","cited_by_count":10,"area":null},{"id":"2203.16202","title":"Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation","created":"2022-03-30","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":"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":"2303.15718","title":"MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction","created":"2023-03-28","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":"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":"2204.08154","title":"End-to-end Weakly-supervised Single-stage Multiple 3D Hand Mesh Reconstruction from a Single RGB Image","created":"2022-04-18","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":"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":"2204.03328","title":"A Comprehensive Review of Sign Language Recognition: Different Types, Modalities, and Datasets","created":"2022-04-07","cited_by_count":5,"area":null},{"id":"2208.09815","title":"LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction","created":"2022-08-21","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":"2407.12307","title":"Weakly-Supervised 3D Hand Reconstruction with Knowledge Prior and Uncertainty Guidance","created":"2024-07-17","cited_by_count":5,"area":null},{"id":"2211.03587","title":"Generalized Product-of-Experts for Learning Multimodal Representations in Noisy Environments","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2308.01088","title":"Hand tracking for clinical applications: validation of the Google MediaPipe Hand (GMH) and the depth-enhanced GMH-D frameworks","created":"2023-08-02","cited_by_count":4,"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":"2202.09450","title":"Modern Augmented Reality: Applications, Trends, and Future Directions","created":"2022-02-18","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":"2311.16552","title":"HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors","created":"2023-11-28","cited_by_count":3,"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":"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":"2505.02079","title":"HandOcc: NeRF-based Hand Rendering with Occupancy Networks","created":"2025-05-04","cited_by_count":2,"area":null},{"id":"2508.08269","title":"emg2tendon: From sEMG Signals to Tendon Control in Musculoskeletal Hands","created":"2025-07-29","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":"2101.03525","title":"Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions","created":"2021-01-10","cited_by_count":1,"area":null},{"id":"2103.04731","title":"Self-Augmented Multi-Modal Feature Embedding","created":"2021-03-08","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":"2206.01384","title":"End-to-End 3D Hand Pose Estimation from Stereo Cameras","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2301.05297","title":"Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2404.05414","title":"Two Hands Are Better Than One: Resolving Hand to Hand Intersections via Occupancy Networks","created":"2024-04-08","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":"2104.12123","title":"Parallel mesh reconstruction streams for pose estimation of interacting hands","created":"2021-04-25","cited_by_count":0,"area":null},{"id":"2203.07881","title":"LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2210.10428","title":"MC-hands-1M: A glove-wearing hand dataset for pose estimation","created":"2022-10-19","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":"2506.11133","title":"Monocular 3D Hand Pose Estimation with Implicit Camera Alignment","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2608.10600","title":"BooST: Bridging Semantics and Motions for Efficient Skill Transfer","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.10743","title":"MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}