{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"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":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"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":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"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":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"1905.03244","title":"Convolutional Mesh Regression for Single-Image Human Shape Reconstruction","created":"2019-05-08","cited_by_count":270},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2008.09047","title":"Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose","created":"2020-08-20","cited_by_count":248},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1804.04875","title":"BodyNet: Volumetric Inference of 3D Human Body Shapes","created":"2018-04-13","cited_by_count":141},{"id":"1805.10483","title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","created":"2018-05-26","cited_by_count":138},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"1711.06753","title":"Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks","created":"2017-11-17","cited_by_count":109},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2003.10350","title":"Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows","created":"2020-03-23","cited_by_count":94},{"id":"1702.07432","title":"Multi-Context Attention for Human Pose Estimation","created":"2017-02-24","cited_by_count":66},{"id":"2006.05734","title":"3D Human Mesh Regression with Dense Correspondence","created":"2020-06-10","cited_by_count":66},{"id":"1708.01101","title":"Learning Feature Pyramids for Human Pose Estimation","created":"2017-08-03","cited_by_count":57},{"id":"2007.11864","title":"Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation","created":"2020-07-23","cited_by_count":52},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"id":"2105.06152","title":"When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks","created":"2021-05-13","cited_by_count":41},{"id":"2110.03480","title":"Learning to Regress Bodies from Images using Differentiable Semantic Rendering","created":"2021-10-07","cited_by_count":39},{"id":"1903.09214","title":"Multi-person Articulated Tracking with Spatial and Temporal Embeddings","created":"2019-03-21","cited_by_count":38},{"id":"2109.05885","title":"Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images","created":"2021-09-13","cited_by_count":38},{"id":"2105.10154","title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","created":"2021-05-21","cited_by_count":26},{"id":"1909.13423","title":"Single-Network Whole-Body Pose Estimation","created":"2019-09-30","cited_by_count":24},{"id":"1910.11535","title":"TRB: A Novel Triplet Representation for Understanding 2D Human Body","created":"2019-10-25","cited_by_count":10}],"next_cursor":null}