{"list":"other","total":65,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"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":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1812.11788","title":"PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation","created":"2018-12-31","cited_by_count":385},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1904.04717","title":"Label Propagation for Deep Semi-supervised Learning","created":"2019-04-09","cited_by_count":289},{"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":"1711.10006","title":"SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again","created":"2017-11-27","cited_by_count":243},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"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":"1805.04092","title":"Learning to Estimate 3D Human Pose and Shape from a Single Color Image","created":"2018-05-10","cited_by_count":226},{"id":"1703.10896","title":"BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth","created":"2017-03-31","cited_by_count":225},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1711.08848","title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","created":"2017-11-24","cited_by_count":210},{"id":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"1903.00812","title":"3D Hand Shape and Pose Estimation from a Single RGB Image","created":"2019-03-03","cited_by_count":174},{"id":"1912.11913","title":"Category-Level Articulated Object Pose Estimation","created":"2019-12-26","cited_by_count":159},{"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":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","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":"1712.04440","title":"Data Distillation: Towards Omni-Supervised Learning","created":"2017-12-12","cited_by_count":126},{"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":"1910.03135","title":"DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System","created":"2019-10-07","cited_by_count":114},{"id":"2004.00060","title":"HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation","created":"2020-03-31","cited_by_count":112},{"id":"1804.09534","title":"Hand Pose Estimation via Latent 2.5D Heatmap Regression","created":"2018-04-25","cited_by_count":111},{"id":"2003.09572","title":"Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data","created":"2020-03-21","cited_by_count":106},{"id":"1812.02541","title":"Segmentation-driven 6D Object Pose Estimation","created":"2018-12-06","cited_by_count":104},{"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":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"1803.11404","title":"Cross-modal Deep Variational Hand Pose Estimation","created":"2018-03-30","cited_by_count":89},{"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":"1701.01909","title":"Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies","created":"2017-01-08","cited_by_count":76},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"2006.15561","title":"Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion","created":"2020-06-28","cited_by_count":39},{"id":"2008.03285","title":"Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning","created":"2020-08-07","cited_by_count":37},{"id":"2010.15831","title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","created":"2020-10-29","cited_by_count":31},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"1903.10883","title":"Generalized Feedback Loop for Joint Hand-Object Pose Estimation","created":"2019-03-25","cited_by_count":22},{"id":"1712.03917","title":"Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals","created":"2017-12-11","cited_by_count":21},{"id":"1412.0065","title":"3D Hand Pose Detection in Egocentric RGB-D Images","created":"2014-11-29","cited_by_count":17},{"id":"1609.03773","title":"Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups","created":"2016-09-13","cited_by_count":10},{"id":"2006.06234","title":"Revisiting the Continuity of Rotation Representations in Neural Networks","created":"2020-06-11","cited_by_count":9}],"next_cursor":null}