{"list":"other","total":71,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"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":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"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":"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":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"2112.03028","title":"D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions","created":"2021-12-01","cited_by_count":113},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2203.14564","title":"HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network","created":"2022-03-28","cited_by_count":96},{"id":"2203.09364","title":"Interacting Attention Graph for Single Image Two-Hand Reconstruction","created":"2022-03-17","cited_by_count":87},{"id":"1904.03419","title":"Context-aware Human Motion Prediction","created":"2019-04-06","cited_by_count":84},{"id":"2204.12490","title":"From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation","created":"2022-04-26","cited_by_count":82},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"2112.02753","title":"MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image","created":"2021-12-06","cited_by_count":74},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70},{"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":"2303.15469","title":"CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis","created":"2023-03-25","cited_by_count":56},{"id":"2309.03891","title":"ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation","created":"2023-09-07","cited_by_count":55},{"id":"2310.03740","title":"ContactGen: Generative Contact Modeling for Grasp Generation","created":"2023-10-05","cited_by_count":53},{"id":"2104.04029","title":"TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild","created":"2021-04-08","cited_by_count":52},{"id":"2109.11399","title":"A Skeleton-Driven Neural Occupancy Representation for Articulated Hands","created":"2021-09-23","cited_by_count":50},{"id":"2309.08942","title":"AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose","created":"2023-09-16","cited_by_count":49},{"id":"2204.09290","title":"Human-Object Interaction Detection via Disentangled Transformer","created":"2022-04-20","cited_by_count":40},{"id":"2207.05053","title":"Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations","created":"2022-07-11","cited_by_count":34},{"id":"2303.17592","title":"Learning Human-to-Robot Handovers from Point Clouds","created":"2023-03-30","cited_by_count":34},{"id":"1908.08391","title":"Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks","created":"2019-08-22","cited_by_count":29},{"id":"2210.03954","title":"Contact-aware Human Motion Forecasting","created":"2022-10-08","cited_by_count":27},{"id":"2303.05095","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","created":"2023-03-09","cited_by_count":26},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24},{"id":"2206.12612","title":"Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions","created":"2022-06-25","cited_by_count":21},{"id":"2210.09245","title":"Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraint","created":"2022-10-17","cited_by_count":21},{"id":"2111.01936","title":"Revisiting spatio-temporal layouts for compositional action recognition","created":"2021-11-02","cited_by_count":19},{"id":"2104.11466","title":"H2O: A Benchmark for Visual Human-human Object Handover Analysis","created":"2021-04-23","cited_by_count":16},{"id":"2303.09806","title":"DexRepNet: Learning Dexterous Robotic Grasping Network with Geometric and Spatial Hand-Object Representations","created":"2023-03-17","cited_by_count":16},{"id":"2305.01618","title":"ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation","created":"2023-05-02","cited_by_count":16},{"id":"2203.14272","title":"Discovering Human-Object Interaction Concepts via Self-Compositional Learning","created":"2022-03-27","cited_by_count":15},{"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},{"id":"2209.12890","title":"It Takes Two: Learning to Plan for Human-Robot Cooperative Carrying","created":"2022-09-26","cited_by_count":12},{"id":"2301.07652","title":"HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects","created":"2023-01-18","cited_by_count":12},{"id":"1606.06854","title":"Model-based Deep Hand Pose Estimation","created":"2016-06-22","cited_by_count":11},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10},{"id":"2208.09224","title":"SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Prediction","created":"2022-08-19","cited_by_count":6},{"id":"2305.02673","title":"Modelling Spatio-Temporal Interactions For Compositional Action Recognition","created":"2023-05-04","cited_by_count":1}],"next_cursor":null}