{"list":"other","total":53,"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"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":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"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":"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":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"1905.12365","title":"Disentangling Monocular 3D Object Detection","created":"2019-05-29","cited_by_count":217},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"1604.01850","title":"Joint Detection and Identification Feature Learning for Person Search","created":"2016-04-07","cited_by_count":190},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"1905.00538","title":"DPSNet: End-to-end Deep Plane Sweep Stereo","created":"2019-05-02","cited_by_count":115},{"id":"2007.14557","title":"Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking","created":"2020-07-29","cited_by_count":115},{"id":"2006.07327","title":"GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning","created":"2020-06-12","cited_by_count":113},{"id":"2007.14772","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","created":"2020-07-29","cited_by_count":108},{"id":"1802.01218","title":"Efficient Video Object Segmentation via Network Modulation","created":"2018-02-04","cited_by_count":98},{"id":"1810.11780","title":"Deep Affinity Network for Multiple Object Tracking","created":"2018-10-28","cited_by_count":82},{"id":"1902.00749","title":"Online Multi-Object Tracking with Dual Matching Attention Networks","created":"2019-02-02","cited_by_count":77},{"id":"1610.06136","title":"POI: Multiple Object Tracking with High Performance Detection and Appearance Feature","created":"2016-10-19","cited_by_count":74},{"id":"1904.11489","title":"Spatial-Temporal Relation Networks for Multi-Object Tracking","created":"2019-04-25","cited_by_count":74},{"id":"2006.05683","title":"TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model","created":"2020-06-10","cited_by_count":70},{"id":"2003.13870","title":"RetinaTrack: Online Single Stage Joint Detection and Tracking","created":"2020-03-30","cited_by_count":67},{"id":"1704.07325","title":"Accurate Optical Flow via Direct Cost Volume Processing","created":"2017-04-24","cited_by_count":66},{"id":"1911.09516","title":"Learning Spatial Fusion for Single-Shot Object Detection","created":"2019-11-21","cited_by_count":59},{"id":"1803.05549","title":"Object Detection in Video with Spatiotemporal Sampling Networks","created":"2018-03-15","cited_by_count":57},{"id":"2003.13743","title":"Combining detection and tracking for human pose estimation in videos","created":"2020-03-30","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":"1706.08482","title":"Deep Network Flow for Multi-Object Tracking","created":"2017-06-26","cited_by_count":45},{"id":"1807.08107","title":"Person Search via A Mask-Guided Two-Stream CNN Model","created":"2018-07-21","cited_by_count":44},{"id":"1906.04016","title":"Learning Temporal Pose Estimation from Sparsely-Labeled Videos","created":"2019-06-06","cited_by_count":39},{"id":"2007.01550","title":"Segment as Points for Efficient Online Multi-Object Tracking and Segmentation","created":"2020-07-03","cited_by_count":36},{"id":"1604.03513","title":"Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids","created":"2016-04-12","cited_by_count":34},{"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":"1912.02096","title":"Learning Multi-Object Tracking and Segmentation from Automatic Annotations","created":"2019-12-04","cited_by_count":27},{"id":"1811.11167","title":"Integrated Object Detection and Tracking with Tracklet-Conditioned Detection","created":"2018-11-27","cited_by_count":17},{"id":"2007.03560","title":"Single Shot Video Object Detector","created":"2020-07-07","cited_by_count":7}],"next_cursor":null}