{"list":"other","total":75,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"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":"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":"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":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"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":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"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":"1705.01583","title":"VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera","created":"2017-05-03","cited_by_count":129},{"id":"1903.06593","title":"PifPaf: Composite Fields for Human Pose Estimation","created":"2019-03-15","cited_by_count":120},{"id":"1511.06645","title":"DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation","created":"2015-11-20","cited_by_count":117},{"id":"1704.02447","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","created":"2017-04-08","cited_by_count":115},{"id":"1612.06524","title":"3D Human Pose Estimation = 2D Pose Estimation + Matching","created":"2016-12-20","cited_by_count":113},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112},{"id":"1905.04266","title":"Exploiting temporal context for 3D human pose estimation in the wild","created":"2019-05-10","cited_by_count":110},{"id":"1805.04095","title":"Ordinal Depth Supervision for 3D Human Pose Estimation","created":"2018-05-10","cited_by_count":107},{"id":"1605.03170","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","created":"2016-05-10","cited_by_count":96},{"id":"1904.04812","title":"Unsupervised 3D Pose Estimation with Geometric Self-Supervision","created":"2019-04-09","cited_by_count":95},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"1904.05547","title":"Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network","created":"2019-04-11","cited_by_count":92},{"id":"1711.08585","title":"Exploiting temporal information for 3D pose estimation","created":"2017-11-23","cited_by_count":89},{"id":"1803.00455","title":"LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images","created":"2018-03-01","cited_by_count":88},{"id":"1908.07172","title":"Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation","created":"2019-08-20","cited_by_count":87},{"id":"1803.09722","title":"3D Human Pose Estimation in the Wild by Adversarial Learning","created":"2018-03-26","cited_by_count":86},{"id":"1902.09868","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","created":"2019-02-26","cited_by_count":85},{"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":"2006.07778","title":"Cascaded deep monocular 3D human pose estimation with evolutionary training data","created":"2020-06-14","cited_by_count":80},{"id":"1904.01324","title":"Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking","created":"2019-04-02","cited_by_count":76},{"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":"2012.15175","title":"Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation","created":"2020-12-30","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":"1511.09439","title":"Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video","created":"2015-11-30","cited_by_count":54},{"id":"2004.11822","title":"3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training","created":"2020-04-07","cited_by_count":54},{"id":"2007.11864","title":"Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation","created":"2020-07-23","cited_by_count":52},{"id":"2008.11469","title":"SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation","created":"2020-08-26","cited_by_count":52},{"id":"1808.08180","title":"MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose Estimation","created":"2018-08-24","cited_by_count":49},{"id":"1611.07727","title":"PoseTrack: Joint Multi-Person Pose Estimation and Tracking","created":"2016-11-23","cited_by_count":44},{"id":"2008.00206","title":"HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation","created":"2020-08-01","cited_by_count":44},{"id":"1906.06059","title":"MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation","created":"2019-06-14","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":"2004.00329","title":"Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation","created":"2020-04-01","cited_by_count":36},{"id":"1912.08077","title":"Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition","created":"2019-12-15","cited_by_count":35},{"id":"2007.02054","title":"Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation","created":"2020-07-04","cited_by_count":35},{"id":"2007.13666","title":"3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning","created":"2020-07-27","cited_by_count":28},{"id":"1612.01465","title":"ArtTrack: Articulated Multi-person Tracking in the Wild","created":"2016-12-05","cited_by_count":27},{"id":"2011.09192","title":"Game Plan: What AI can do for Football, and What Football can do for AI","created":"2020-11-18","cited_by_count":27},{"id":"2010.06449","title":"A review of 3D human pose estimation algorithms for markerless motion capture","created":"2020-10-13","cited_by_count":24},{"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":"2004.12652","title":"Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos","created":"2020-04-27","cited_by_count":22},{"id":"2101.02471","title":"PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation","created":"2021-01-07","cited_by_count":22},{"id":"1806.01484","title":"3D Human Pose Estimation with 2D Marginal Heatmaps","created":"2018-06-05","cited_by_count":20},{"id":"2007.08943","title":"HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization","created":"2020-07-17","cited_by_count":20},{"id":"2104.01797","title":"Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks","created":"2021-04-05","cited_by_count":16},{"id":"1507.05699","title":"Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians","created":"2015-07-21","cited_by_count":14},{"id":"2003.03473","title":"PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation","created":"2020-03-07","cited_by_count":8},{"id":"2010.06844","title":"Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization","created":"2020-10-13","cited_by_count":2}],"next_cursor":null}