{"list":"other","total":64,"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":"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":"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1808.00671","title":"PCN: Point Completion Network","created":"2018-08-02","cited_by_count":384},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1612.05424","title":"Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks","created":"2016-12-16","cited_by_count":308},{"id":"1804.06516","title":"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization","created":"2018-04-18","cited_by_count":294},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"1604.03628","title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","created":"2016-04-13","cited_by_count":205},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"1610.01983","title":"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?","created":"2016-10-06","cited_by_count":194},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"1709.07322","title":"Playing for Benchmarks","created":"2017-09-21","cited_by_count":169},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"1511.04136","title":"UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking","created":"2015-11-13","cited_by_count":98},{"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":"1807.09190","title":"PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation","created":"2018-07-24","cited_by_count":81},{"id":"1903.01568","title":"The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes","created":"2019-03-04","cited_by_count":80},{"id":"1604.07866","title":"Learning by tracking: Siamese CNN for robust target association","created":"2016-04-26","cited_by_count":79},{"id":"1811.10742","title":"Joint Monocular 3D Vehicle Detection and Tracking","created":"2018-11-26","cited_by_count":77},{"id":"1906.06618","title":"How To Train Your Deep Multi-Object Tracker","created":"2019-06-15","cited_by_count":71},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67},{"id":"2006.14550","title":"Lifted Disjoint Paths with Application in Multiple Object Tracking","created":"2020-06-25","cited_by_count":55},{"id":"1708.02843","title":"Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism","created":"2017-08-09","cited_by_count":48},{"id":"1711.02741","title":"Recurrent Autoregressive Networks for Online Multi-Object Tracking","created":"2017-11-07","cited_by_count":48},{"id":"1706.08482","title":"Deep Network Flow for Multi-Object Tracking","created":"2017-06-26","cited_by_count":45},{"id":"1801.06397","title":"What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?","created":"2018-01-19","cited_by_count":44},{"id":"2103.07889","title":"Learning a Proposal Classifier for Multiple Object Tracking","created":"2021-03-14","cited_by_count":42},{"id":"2004.00329","title":"Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation","created":"2020-04-01","cited_by_count":36},{"id":"2003.11291","title":"A Unified Object Motion and Affinity Model for Online Multi-Object Tracking","created":"2020-03-25","cited_by_count":33},{"id":"1511.07041","title":"SceneNet: Understanding Real World Indoor Scenes With Synthetic Data","created":"2015-11-22","cited_by_count":29},{"id":"1809.07357","title":"Combined Image- and World-Space Tracking in Traffic Scenes","created":"2018-09-19","cited_by_count":29},{"id":"2008.08826","title":"Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking","created":"2020-08-20","cited_by_count":25},{"id":"1611.05244","title":"Deep Transfer Learning for Person Re-identification","created":"2016-11-16","cited_by_count":16},{"id":"2006.13164","title":"Joint Object Detection and Multi-Object Tracking with Graph Neural Networks","created":"2020-06-23","cited_by_count":14},{"id":"1907.06922","title":"Human Pose Estimation for Real-World Crowded Scenarios","created":"2019-07-16","cited_by_count":9},{"id":"2001.03032","title":"Virtual to Real adaptation of Pedestrian Detectors","created":"2020-01-09","cited_by_count":9},{"id":"2004.07472","title":"SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking","created":"2020-04-16","cited_by_count":4}],"next_cursor":null}