{"list":"other","total":72,"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"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":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"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":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"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":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"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":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"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":"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":"1904.07399","title":"Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression","created":"2019-04-16","cited_by_count":128},{"id":"2012.14214","title":"TransPose: Keypoint Localization via Transformer","created":"2020-12-28","cited_by_count":126},{"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":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","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":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1605.03170","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","created":"2016-05-10","cited_by_count":96},{"id":"1908.09220","title":"Single-Stage Multi-Person Pose Machines","created":"2019-08-24","cited_by_count":95},{"id":"2003.12737","title":"Actor-Transformers for Group Activity Recognition","created":"2020-03-28","cited_by_count":84},{"id":"1807.03146","title":"Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning","created":"2018-07-05","cited_by_count":79},{"id":"2012.15175","title":"Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation","created":"2020-12-30","cited_by_count":69},{"id":"1803.04108","title":"Style Aggregated Network for Facial Landmark Detection","created":"2018-03-12","cited_by_count":60},{"id":"2007.02846","title":"Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation","created":"2020-07-06","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":"1707.05388","title":"Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation","created":"2017-07-17","cited_by_count":48},{"id":"2004.09927","title":"TTNet: Real-time temporal and spatial video analysis of table tennis","created":"2020-04-21","cited_by_count":36},{"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":"1811.11975","title":"Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields","created":"2018-11-29","cited_by_count":32},{"id":"1608.08526","title":"Multi-Person Pose Estimation with Local Joint-to-Person Associations","created":"2016-08-30","cited_by_count":18},{"id":"2110.05132","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","created":"2021-10-11","cited_by_count":18},{"id":"2007.09590","title":"AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation","created":"2020-07-19","cited_by_count":17},{"id":"2007.03221","title":"AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses","created":"2020-07-07","cited_by_count":10},{"id":"1902.01831","title":"Face Alignment using a 3D Deeply-initialized Ensemble of Regression Trees","created":"2019-02-05","cited_by_count":8},{"id":"1910.00754","title":"Joint Learning of Semantic Alignment and Object Landmark Detection","created":"2019-10-02","cited_by_count":6},{"id":"2011.08446","title":"EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer","created":"2020-11-17","cited_by_count":5},{"id":"1912.05107","title":"PuckNet: Estimating hockey puck location from broadcast video","created":"2019-12-11","cited_by_count":2},{"id":"2105.09880","title":"DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera","created":"2021-05-20","cited_by_count":2},{"id":"1902.10024","title":"STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection","created":"2019-02-26","cited_by_count":1}],"next_cursor":null}