{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"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":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"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":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2008.09309","title":"InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image","created":"2020-08-21","cited_by_count":245},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","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":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"2007.09545","title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose","created":"2020-07-19","cited_by_count":183},{"id":"2201.02610","title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","created":"2022-01-07","cited_by_count":181},{"id":"2011.08627","title":"Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video","created":"2020-11-17","cited_by_count":163},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141},{"id":"2004.13449","title":"Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction","created":"2020-04-28","cited_by_count":139},{"id":"2209.15397","title":"KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way","created":"2022-09-30","cited_by_count":132},{"id":"1902.09305","title":"End-to-end Hand Mesh Recovery from a Monocular RGB Image","created":"2019-02-25","cited_by_count":124},{"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":"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":"2003.09282","title":"Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints","created":"2020-03-20","cited_by_count":97},{"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":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"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":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"1610.04889","title":"Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input","created":"2016-10-16","cited_by_count":56},{"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":"1704.02612","title":"BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis","created":"2017-04-09","cited_by_count":46},{"id":"1812.01002","title":"Disentangling Latent Hands for Image Synthesis and Pose Estimation","created":"2018-12-03","cited_by_count":44},{"id":"2003.04645","title":"HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images","created":"2020-03-10","cited_by_count":41},{"id":"1907.10303","title":"Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation","created":"2019-07-24","cited_by_count":36},{"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},{"id":"2007.05168","title":"SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation","created":"2020-07-10","cited_by_count":34},{"id":"2006.01320","title":"Two-hand Global 3D Pose Estimation Using Monocular RGB","created":"2020-06-01","cited_by_count":27},{"id":"1810.01845","title":"Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation","created":"2018-10-03","cited_by_count":25},{"id":"2208.07308","title":"Pose Forecasting in Industrial Human-Robot Collaboration","created":"2022-07-24","cited_by_count":25},{"id":"2106.11725","title":"RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video","created":"2021-06-22","cited_by_count":23},{"id":"1902.10892","title":"Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrum","created":"2019-02-28","cited_by_count":22},{"id":"2303.04991","title":"Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation","created":"2023-03-09","cited_by_count":21},{"id":"2103.00760","title":"Self-Supervised Depth and Ego-Motion Estimation for Monocular Thermal Video Using Multi-Spectral Consistency Loss","created":"2021-03-01","cited_by_count":16},{"id":"2108.05545","title":"HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton","created":"2021-08-12","cited_by_count":16},{"id":"2205.13278","title":"Semantic Segmentation for Thermal Images: A Comparative Survey","created":"2022-05-26","cited_by_count":16},{"id":"1909.07231","title":"DeepTIO: A Deep Thermal-Inertial Odometry with Visual Hallucination","created":"2019-09-16","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":"2104.07196","title":"Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks","created":"2021-04-15","cited_by_count":12},{"id":"2305.01652","title":"Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection","created":"2023-05-02","cited_by_count":10},{"id":"2001.00702","title":"HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation","created":"2020-01-03","cited_by_count":6},{"id":"2307.03623","title":"Robust Human Detection under Visual Degradation via Thermal and mmWave Radar Fusion","created":"2023-07-07","cited_by_count":3}],"next_cursor":null}