{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1909.12828","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","created":"2019-09-27","cited_by_count":627},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"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":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"2008.03713","title":"I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image","created":"2020-08-09","cited_by_count":274},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"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":"2008.12272","title":"Monocular, One-stage, Regression of Multiple 3D People","created":"2020-08-27","cited_by_count":218},{"id":"1701.02468","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","created":"2017-01-10","cited_by_count":205},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2008.08535","title":"STAR: Sparse Trained Articulated Human Body Regressor","created":"2020-08-19","cited_by_count":194},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"1808.05942","title":"Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation","created":"2018-08-17","cited_by_count":185},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"1709.07322","title":"Playing for Benchmarks","created":"2017-09-21","cited_by_count":169},{"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":"1905.04266","title":"Exploiting temporal context for 3D human pose estimation in the wild","created":"2019-05-10","cited_by_count":110},{"id":"2008.03789","title":"3D Human Motion Estimation via Motion Compression and Refinement","created":"2020-08-09","cited_by_count":98},{"id":"1707.07548","title":"Towards Accurate Markerless Human Shape and Pose Estimation over Time","created":"2017-07-24","cited_by_count":92},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"id":"1803.08319","title":"Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World","created":"2018-03-22","cited_by_count":82},{"id":"2009.10013","title":"Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild","created":"2020-09-21","cited_by_count":82},{"id":"2008.08474","title":"Human Body Model Fitting by Learned Gradient Descent","created":"2020-08-19","cited_by_count":81},{"id":"1907.02499","title":"Sim2real transfer learning for 3D human pose estimation: motion to the rescue","created":"2019-07-04","cited_by_count":76},{"id":"2003.04232","title":"Hierarchical Kinematic Human Mesh Recovery","created":"2020-03-09","cited_by_count":71},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69},{"id":"1907.00837","title":"XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera","created":"2019-07-01","cited_by_count":68},{"id":"1904.04571","title":"3DPeople: Modeling the Geometry of Dressed Humans","created":"2019-04-09","cited_by_count":58},{"id":"2012.09843","title":"Human Mesh Recovery from Multiple Shots","created":"2020-12-17","cited_by_count":52},{"id":"1511.06789","title":"The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition","created":"2015-11-20","cited_by_count":48},{"id":"2103.16449","title":"Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction","created":"2021-03-30","cited_by_count":39},{"id":"1908.06442","title":"Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild","created":"2019-08-18","cited_by_count":38},{"id":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38},{"id":"2009.06549","title":"Beyond Weak Perspective for Monocular 3D Human Pose Estimation","created":"2020-09-14","cited_by_count":29},{"id":"2007.08032","title":"When and how CNNs generalize to out-of-distribution category-viewpoint combinations","created":"2020-07-15","cited_by_count":22},{"id":"2105.13965","title":"Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation","created":"2021-05-28","cited_by_count":19},{"id":"2012.02743","title":"SMPLy Benchmarking 3D Human Pose Estimation in the Wild","created":"2020-12-04","cited_by_count":16},{"id":"1908.00967","title":"Learning to Train with Synthetic Humans","created":"2019-08-02","cited_by_count":14},{"id":"2007.14878","title":"MessyTable: Instance Association in Multiple Camera Views","created":"2020-07-29","cited_by_count":13},{"id":"2012.14739","title":"Chasing the Tail in Monocular 3D Human Reconstruction with Prototype Memory","created":"2020-12-29","cited_by_count":11}],"next_cursor":null}