{"list":"other","total":60,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"id":"1903.00621","title":"Feature Selective Anchor-Free Module for Single-Shot Object Detection","created":"2019-03-02","cited_by_count":139},{"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":"1701.06659","title":"DSSD : Deconvolutional Single Shot Detector","created":"2017-01-23","cited_by_count":131},{"id":"1711.06897","title":"Single-Shot Refinement Neural Network for Object Detection","created":"2017-11-18","cited_by_count":129},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"1909.02466","title":"FreeAnchor: Learning to Match Anchors for Visual Object Detection","created":"2019-09-05","cited_by_count":90},{"id":"1901.03278","title":"Region Proposal by Guided Anchoring","created":"2019-01-10","cited_by_count":87},{"id":"1906.04016","title":"Learning Temporal Pose Estimation from Sparsely-Labeled Videos","created":"2019-06-06","cited_by_count":39},{"id":"2007.11056","title":"BorderDet: Border Feature for Dense Object Detection","created":"2020-07-21","cited_by_count":39},{"id":"1807.01696","title":"Localization Recall Precision (LRP): A New Performance Metric for Object Detection","created":"2018-07-04","cited_by_count":31},{"id":"2010.15831","title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","created":"2020-10-29","cited_by_count":31},{"id":"1903.09126","title":"Progressive Sparse Local Attention for Video object detection","created":"2019-03-21","cited_by_count":30},{"id":"1704.05776","title":"Accurate Single Stage Detector Using Recurrent Rolling Convolution","created":"2017-04-19","cited_by_count":27},{"id":"2007.02355","title":"HoughNet: Integrating near and long-range evidence for bottom-up object detection","created":"2020-07-05","cited_by_count":20},{"id":"1604.04693","title":"Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection","created":"2016-04-16","cited_by_count":17},{"id":"1708.02863","title":"CoupleNet: Coupling Global Structure with Local Parts for Object Detection","created":"2017-08-09","cited_by_count":16},{"id":"2011.10772","title":"One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks","created":"2020-11-21","cited_by_count":15},{"id":"1408.0814","title":"Object Detection Through Exploration With A Foveated Visual Field","created":"2014-08-04","cited_by_count":14},{"id":"1603.08212","title":"Human Pose Estimation using Deep Consensus Voting","created":"2016-03-27","cited_by_count":14},{"id":"1909.03812","title":"HoughNet: neural network architecture for vanishing points detection","created":"2019-09-09","cited_by_count":5}],"next_cursor":null}