{"list":"other","total":89,"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":"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"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":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"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":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"1910.06278","title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","created":"2019-10-14","cited_by_count":165},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1907.11346","title":"Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image","created":"2019-07-26","cited_by_count":132},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"1406.2984","title":"Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation","created":"2014-06-11","cited_by_count":129},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"id":"1507.06550","title":"Human Pose Estimation with Iterative Error Feedback","created":"2015-07-23","cited_by_count":121},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112},{"id":"1803.10683","title":"Pose2Seg: Detection Free Human Instance Segmentation","created":"2018-03-28","cited_by_count":107},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"2103.16385","title":"Graph Stacked Hourglass Networks for 3D Human Pose Estimation","created":"2021-03-30","cited_by_count":95},{"id":"2007.09389","title":"SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach","created":"2020-07-18","cited_by_count":94},{"id":"2105.02465","title":"PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation","created":"2021-05-06","cited_by_count":89},{"id":"2006.07778","title":"Cascaded deep monocular 3D human pose estimation with evolutionary training data","created":"2020-06-14","cited_by_count":80},{"id":"1911.07524","title":"The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation","created":"2019-11-18","cited_by_count":79},{"id":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"id":"2012.15175","title":"Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation","created":"2020-12-30","cited_by_count":69},{"id":"2003.07581","title":"Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild","created":"2020-03-17","cited_by_count":66},{"id":"2003.04030","title":"Learning Delicate Local Representations for Multi-Person Pose Estimation","created":"2020-03-09","cited_by_count":65},{"id":"1901.00148","title":"Rethinking on Multi-Stage Networks for Human Pose Estimation","created":"2019-01-01","cited_by_count":58},{"id":"1708.01101","title":"Learning Feature Pyramids for Human Pose Estimation","created":"2017-08-03","cited_by_count":57},{"id":"2007.02846","title":"Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation","created":"2020-07-06","cited_by_count":57},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"1609.01743","title":"Human pose estimation via Convolutional Part Heatmap Regression","created":"2016-09-06","cited_by_count":51},{"id":"1911.07451","title":"DirectPose: Direct End-to-End Multi-Person Pose Estimation","created":"2019-11-18","cited_by_count":49},{"id":"2001.08095","title":"UniPose: Unified Human Pose Estimation in Single Images and Videos","created":"2020-01-22","cited_by_count":49},{"id":"1807.04067","title":"MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network","created":"2018-07-11","cited_by_count":47},{"id":"1812.03595","title":"PoseFix: Model-agnostic General Human Pose Refinement Network","created":"2018-12-10","cited_by_count":47},{"id":"1805.09707","title":"Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation","created":"2018-05-24","cited_by_count":44},{"id":"2201.07412","title":"Poseur: Direct Human Pose Regression with Transformers","created":"2022-01-19","cited_by_count":43},{"id":"2010.13302","title":"AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild","created":"2020-10-26","cited_by_count":40},{"id":"2106.03772","title":"Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking","created":"2021-06-07","cited_by_count":37},{"id":"1705.00389","title":"Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation","created":"2017-04-30","cited_by_count":35},{"id":"1905.03466","title":"Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information","created":"2019-05-09","cited_by_count":35},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34},{"id":"2007.10599","title":"Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement","created":"2020-07-21","cited_by_count":33},{"id":"1912.00821","title":"Mixture Dense Regression for Object Detection and Human Pose Estimation","created":"2019-12-02","cited_by_count":29},{"id":"2105.04154","title":"Unsupervised Human Pose Estimation through Transforming Shape Templates","created":"2021-05-10","cited_by_count":26},{"id":"2003.10506","title":"Peeking into occluded joints: A novel framework for crowd pose estimation","created":"2020-03-23","cited_by_count":25},{"id":"2012.11806","title":"Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos","created":"2020-12-22","cited_by_count":23},{"id":"1505.06606","title":"Robust Optimization for Deep Regression","created":"2015-05-25","cited_by_count":22},{"id":"2002.11098","title":"Toward fast and accurate human pose estimation via soft-gated skip connections","created":"2020-02-25","cited_by_count":22},{"id":"2008.00697","title":"Adversarial Semantic Data Augmentation for Human Pose Estimation","created":"2020-08-03","cited_by_count":22},{"id":"1901.01760","title":"Human Pose Estimation with Spatial Contextual Information","created":"2019-01-07","cited_by_count":21},{"id":"2011.12498","title":"An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation","created":"2020-11-25","cited_by_count":21},{"id":"1804.07909","title":"Learning to Refine Human Pose Estimation","created":"2018-04-21","cited_by_count":19},{"id":"1603.09065","title":"Structured Feature Learning for Pose Estimation","created":"2016-03-30","cited_by_count":17},{"id":"2205.01271","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","created":"2022-05-03","cited_by_count":16},{"id":"1504.07159","title":"Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation","created":"2015-04-27","cited_by_count":14},{"id":"1603.08212","title":"Human Pose Estimation using Deep Consensus Voting","created":"2016-03-27","cited_by_count":14},{"id":"2205.00748","title":"Dual networks based 3D Multi-Person Pose Estimation from Monocular Video","created":"2022-05-02","cited_by_count":13},{"id":"2201.08093","title":"AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation","created":"2022-01-20","cited_by_count":11},{"id":"1709.07220","title":"Human Pose Estimation using Global and Local Normalization","created":"2017-09-21","cited_by_count":10},{"id":"2203.07837","title":"Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation","created":"2022-03-15","cited_by_count":3}],"next_cursor":null}