{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"1802.05384","title":"AtlasNet: A Papier-M\\^ach\\'e Approach to Learning 3D Surface Generation","created":"2018-02-15","cited_by_count":539},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"1705.03550","title":"CORe50: a New Dataset and Benchmark for Continuous Object Recognition","created":"2017-05-09","cited_by_count":289},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"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},{"id":"2108.04444","title":"SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer","created":"2021-08-10","cited_by_count":164},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"2004.01946","title":"Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild","created":"2020-04-04","cited_by_count":146},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","cited_by_count":141},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"2012.00924","title":"CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction","created":"2020-12-02","cited_by_count":128},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"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},{"id":"1904.04196","title":"Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering","created":"2019-04-08","cited_by_count":115},{"id":"1804.09534","title":"Hand Pose Estimation via Latent 2.5D Heatmap Regression","created":"2018-04-25","cited_by_count":111},{"id":"1711.07399","title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map","created":"2017-11-20","cited_by_count":102},{"id":"2204.07153","title":"What's in your hands? 3D Reconstruction of Generic Objects in Hands","created":"2022-04-14","cited_by_count":90},{"id":"2202.00164","title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","created":"2022-02-01","cited_by_count":89},{"id":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87},{"id":"2302.10668","title":"$PC^2$: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction","created":"2023-02-21","cited_by_count":84},{"id":"2311.18448","title":"HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video","created":"2023-11-30","cited_by_count":78},{"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},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74},{"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},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"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},{"id":"2207.12909","title":"AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction","created":"2022-07-26","cited_by_count":59},{"id":"2108.07044","title":"Towards unconstrained joint hand-object reconstruction from RGB videos","created":"2021-08-16","cited_by_count":58},{"id":"1908.09999","title":"A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image","created":"2019-08-27","cited_by_count":56},{"id":"2204.13062","title":"Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution","created":"2022-04-27","cited_by_count":54},{"id":"2304.11970","title":"gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction","created":"2023-04-24","cited_by_count":50},{"id":"2406.09598","title":"Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Tracking","created":"2024-06-13","cited_by_count":48},{"id":"2207.11061","title":"3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal","created":"2022-07-22","cited_by_count":36},{"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},{"id":"2211.16835","title":"Reconstructing Hand-Held Objects from Monocular Video","created":"2022-11-30","cited_by_count":35},{"id":"2403.16428","title":"Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects","created":"2024-03-25","cited_by_count":35},{"id":"2404.15709","title":"ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos","created":"2024-04-24","cited_by_count":35},{"id":"2303.17592","title":"Learning Human-to-Robot Handovers from Point Clouds","created":"2023-03-30","cited_by_count":34},{"id":"1905.01326","title":"Single Image 3D Hand Reconstruction with Mesh Convolutions","created":"2019-05-04","cited_by_count":32},{"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},{"id":"2211.16193","title":"In-Hand 3D Object Scanning from an RGB Sequence","created":"2022-11-28","cited_by_count":27},{"id":"2107.00887","title":"HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Dataset","created":"2021-07-02","cited_by_count":26},{"id":"2404.06507","title":"Reconstructing Hand-Held Objects in 3D from Images and Videos","created":"2024-04-09","cited_by_count":24},{"id":"2112.05300","title":"Representing 3D Shapes with Probabilistic Directed Distance Fields","created":"2021-12-10","cited_by_count":21},{"id":"2308.08231","title":"DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field","created":"2023-08-16","cited_by_count":17},{"id":"2011.13607","title":"PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers","created":"2020-11-27","cited_by_count":16},{"id":"2102.09244","title":"HandTailor: Towards High-Precision Monocular 3D Hand Recovery","created":"2021-02-18","cited_by_count":15},{"id":"2111.11704","title":"Deep Point Cloud Reconstruction","created":"2021-11-23","cited_by_count":15},{"id":"2205.09747","title":"HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers","created":"2022-05-19","cited_by_count":15},{"id":"2402.17062","title":"HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields","created":"2024-02-26","cited_by_count":14},{"id":"2311.05599","title":"SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers","created":"2023-11-09","cited_by_count":13},{"id":"2305.03036","title":"3D Reconstruction of Objects in Hands without Real World 3D Supervision","created":"2023-05-04","cited_by_count":12},{"id":"2308.10574","title":"CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation","created":"2023-08-21","cited_by_count":11},{"id":"2305.20089","title":"Learning Explicit Contact for Implicit Reconstruction of Hand-held Objects from Monocular Images","created":"2023-05-31","cited_by_count":10},{"id":"2312.15719","title":"Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos","created":"2023-12-25","cited_by_count":10},{"id":"2006.05927","title":"Recent Advances in 3D Object and Hand Pose Estimation","created":"2020-06-10","cited_by_count":9},{"id":"2409.18364","title":"Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images","created":"2024-09-27","cited_by_count":5},{"id":"2311.14189","title":"D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction","created":"2023-11-23","cited_by_count":3}],"next_cursor":null}