{"total":174,"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":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306,"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":"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":"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":"2104.07645","title":"A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation","created":"2021-04-15","cited_by_count":114,"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":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96,"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":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87,"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":"2103.11703","title":"Model-based 3D Hand Reconstruction via Self-Supervised Learning","created":"2021-03-22","cited_by_count":65,"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":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61,"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":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"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":"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":"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":"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":"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":"2211.16835","title":"Reconstructing Hand-Held Objects from Monocular Video","created":"2022-11-30","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":"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":"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":"2212.09530","title":"HARP: Personalized Hand Reconstruction from a Monocular RGB Video","created":"2022-12-19","cited_by_count":28,"area":null},{"id":"2111.00763","title":"Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements","created":"2021-11-01","cited_by_count":27,"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":"2210.07650","title":"DART: Articulated Hand Model with Diverse Accessories and Rich Textures","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2308.16082","title":"SignDiff: Diffusion Model for American Sign Language Production","created":"2023-08-30","cited_by_count":25,"area":"diffusion"},{"id":"2104.15139","title":"Differentiable Event Stream Simulator for Non-Rigid 3D Tracking","created":"2021-04-30","cited_by_count":23,"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":"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":"2307.05541","title":"High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition","created":"2023-07-08","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":"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":"2102.09244","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","created":"2021-02-18","cited_by_count":15,"area":null},{"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":"2211.08675","title":"XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse","created":"2022-11-16","cited_by_count":14,"area":null},{"id":"2405.02508","title":"Rasterized Edge Gradients: Handling Discontinuities Differentiably","created":"2024-05-03","cited_by_count":14,"area":null},{"id":"2406.01334","title":"HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models","created":"2024-06-03","cited_by_count":14,"area":"diffusion"},{"id":"2105.02173","title":"Learning Feature Aggregation for Deep 3D Morphable Models","created":"2021-05-05","cited_by_count":13,"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":"2405.07933","title":"Authentic Hand Avatar from a Phone Scan via Universal Hand Model","created":"2024-05-13","cited_by_count":13,"area":null},{"id":"2210.05665","title":"HiFECap: Monocular High-Fidelity and Expressive Capture of Human Performances","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2107.01205","title":"HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks","created":"2021-07-02","cited_by_count":11,"area":null},{"id":"2209.10840","title":"Identity-Aware Hand Mesh Estimation and Personalization from RGB Images","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2305.05785","title":"Regular Splitting Graph Network for 3D Human Pose Estimation","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2109.08364","title":"GraFormer: Graph Convolution Transformer for 3D Pose Estimation","created":"2021-09-17","cited_by_count":10,"area":null},{"id":"2304.04038","title":"POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo","created":"2023-04-08","cited_by_count":10,"area":null},{"id":"2308.11015","title":"Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images","created":"2023-08-21","cited_by_count":10,"area":null},{"id":"2309.07891","title":"HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image","created":"2023-09-14","cited_by_count":10,"area":null},{"id":"2407.21510","title":"PEAR: Phrase-Based Hand-Object Interaction Anticipation","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2412.01537","title":"HandOS: 3D Hand Reconstruction in One Stage","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2111.00950","title":"Higher-Order Implicit Fairing Networks for 3D Human Pose Estimation","created":"2021-11-01","cited_by_count":8,"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":"2211.13429","title":"UV-Based 3D Hand-Object Reconstruction with Grasp Optimization","created":"2022-11-24","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":"2312.11894","title":"3D-LFM: Lifting Foundation Model","created":"2023-12-19","cited_by_count":8,"area":null},{"id":"2405.11481","title":"Physics-aware Hand-object Interaction Denoising","created":"2024-05-19","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":"2110.00869","title":"BdSL36: A Dataset for Bangladeshi Sign Letters Recognition","created":"2021-10-02","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":"2502.15251","title":"SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training","created":"2025-02-21","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":"2405.00790","title":"SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators","created":"2024-05-01","cited_by_count":6,"area":null},{"id":"2408.10581","title":"Multi-view Hand Reconstruction with a Point-Embedded Transformer","created":"2024-08-20","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":"2108.13995","title":"RealisticHands: A Hybrid Model for 3D Hand Reconstruction","created":"2021-08-31","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":"2109.14657","title":"Understanding Egocentric Hand-Object Interactions from Hand Pose Estimation","created":"2021-09-29","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":"2210.05870","title":"LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLAD","created":"2022-10-12","cited_by_count":5,"area":null}],"next_cursor":"100"}