{"list":"other","total":55,"rows":[{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"2006.06882","title":"Rethinking Pre-training and Self-training","created":"2020-06-11","cited_by_count":352},{"id":"2106.09018","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","created":"2021-06-16","cited_by_count":316},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"2005.04757","title":"A Simple Semi-Supervised Learning Framework for Object Detection","created":"2020-05-10","cited_by_count":282},{"id":"2102.04803","title":"DetCo: Unsupervised Contrastive Learning for Object Detection","created":"2021-02-09","cited_by_count":205},{"id":"1909.13226","title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","created":"2019-09-29","cited_by_count":188},{"id":"2103.10957","title":"Efficient Visual Pretraining with Contrastive Detection","created":"2021-03-19","cited_by_count":150},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"1712.04440","title":"Data Distillation: Towards Omni-Supervised Learning","created":"2017-12-12","cited_by_count":126},{"id":"2108.06753","title":"Learning Open-World Object Proposals without Learning to Classify","created":"2021-08-15","cited_by_count":109},{"id":"1903.12174","title":"TensorMask: A Foundation for Dense Object Segmentation","created":"2019-03-28","cited_by_count":101},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74},{"id":"1406.5549","title":"Fast Edge Detection Using Structured Forests","created":"2014-06-20","cited_by_count":65},{"id":"2001.05086","title":"Proposal Learning for Semi-Supervised Object Detection","created":"2020-01-15","cited_by_count":55},{"id":"2007.01293","title":"Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning","created":"2020-07-02","cited_by_count":53},{"id":"2003.11712","title":"Mask Encoding for Single Shot Instance Segmentation","created":"2020-03-26","cited_by_count":47},{"id":"1910.04104","title":"Vehicle Re-identification with Viewpoint-aware Metric Learning","created":"2019-10-09","cited_by_count":45},{"id":"2007.09162","title":"Improving Object Detection with Selective Self-supervised Self-training","created":"2020-07-17","cited_by_count":35},{"id":"1803.09867","title":"Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection","created":"2018-03-27","cited_by_count":32},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24},{"id":"2103.17220","title":"Scale-aware Automatic Augmentation for Object Detection","created":"2021-03-31","cited_by_count":23},{"id":"1709.06283","title":"Cartman: The low-cost Cartesian Manipulator that won the Amazon Robotics Challenge","created":"2017-09-19","cited_by_count":19},{"id":"2003.06148","title":"PointINS: Point-based Instance Segmentation","created":"2020-03-13","cited_by_count":17},{"id":"2010.14793","title":"Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation","created":"2020-10-28","cited_by_count":4}],"next_cursor":null}