{"list":"other","total":55,"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"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":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"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":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1811.07628","title":"ATOM: Accurate Tracking by Overlap Maximization","created":"2018-11-19","cited_by_count":285},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"1608.01471","title":"UnitBox: An Advanced Object Detection Network","created":"2016-08-04","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":"1808.06048","title":"Distractor-aware Siamese Networks for Visual Object Tracking","created":"2018-08-18","cited_by_count":187},{"id":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"id":"1911.07241","title":"SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking","created":"2019-11-17","cited_by_count":148},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"1704.06036","title":"End-to-end representation learning for Correlation Filter based tracking","created":"2017-04-20","cited_by_count":90},{"id":"1604.01802","title":"Learning to Track at 100 FPS with Deep Regression Networks","created":"2016-04-06","cited_by_count":89},{"id":"1803.10859","title":"Features for Multi-Target Multi-Camera Tracking and Re-Identification","created":"2018-03-28","cited_by_count":88},{"id":"1810.11780","title":"Deep Affinity Network for Multiple Object Tracking","created":"2018-10-28","cited_by_count":82},{"id":"1604.07866","title":"Learning by tracking: Siamese CNN for robust target association","created":"2016-04-26","cited_by_count":79},{"id":"1701.01909","title":"Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies","created":"2017-01-08","cited_by_count":76},{"id":"1906.06618","title":"How To Train Your Deep Multi-Object Tracker","created":"2019-06-15","cited_by_count":71},{"id":"1812.06148","title":"Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking","created":"2018-12-14","cited_by_count":65},{"id":"1802.08817","title":"A Twofold Siamese Network for Real-Time Object Tracking","created":"2018-02-24","cited_by_count":62},{"id":"1911.07451","title":"DirectPose: Direct End-to-End Multi-Person Pose Estimation","created":"2019-11-18","cited_by_count":49},{"id":"1711.02741","title":"Recurrent Autoregressive Networks for Online Multi-Object Tracking","created":"2017-11-07","cited_by_count":48},{"id":"1504.02340","title":"Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor","created":"2015-04-09","cited_by_count":46},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"1911.12448","title":"Soft Anchor-Point Object Detection","created":"2019-11-27","cited_by_count":42},{"id":"2007.11056","title":"BorderDet: Border Feature for Dense Object Detection","created":"2020-07-21","cited_by_count":39},{"id":"1607.08381","title":"A Siamese Long Short-Term Memory Architecture for Human Re-Identification","created":"2016-07-28","cited_by_count":32},{"id":"1811.07258","title":"Exploit the Connectivity: Multi-Object Tracking with TrackletNet","created":"2018-11-18","cited_by_count":30},{"id":"1802.03596","title":"Deep Meta-Learning: Learning to Learn in the Concept Space","created":"2018-02-10","cited_by_count":22},{"id":"2007.15576","title":"Dense Scene Multiple Object Tracking with Box-Plane Matching","created":"2020-07-30","cited_by_count":7},{"id":"1605.06177","title":"Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art","created":"2016-05-20","cited_by_count":2}],"next_cursor":null}