{"list":"other","total":67,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"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":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"1812.11788","title":"PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation","created":"2018-12-31","cited_by_count":385},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"1901.04780","title":"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion","created":"2019-01-15","cited_by_count":355},{"id":"2203.10638","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","created":"2022-03-20","cited_by_count":320},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119},{"id":"2010.12138","title":"Rethinking the competition between detection and ReID in Multi-Object Tracking","created":"2020-10-23","cited_by_count":101},{"id":"2103.14304","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","created":"2021-03-26","cited_by_count":94},{"id":"2104.00194","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","created":"2021-04-01","cited_by_count":93},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69},{"id":"2003.13870","title":"RetinaTrack: Online Single Stage Joint Detection and Tracking","created":"2020-03-30","cited_by_count":67},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62},{"id":"1711.11577","title":"Towards High Performance Video Object Detection","created":"2017-11-30","cited_by_count":60},{"id":"2102.02267","title":"DEFT: Detection Embeddings for Tracking","created":"2021-02-03","cited_by_count":56},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52},{"id":"2204.07346","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","created":"2022-04-15","cited_by_count":50},{"id":"1907.03961","title":"3D Multi-Object Tracking: A Baseline and New Evaluation Metrics","created":"2019-07-09","cited_by_count":47},{"id":"2103.16178","title":"Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking","created":"2021-03-30","cited_by_count":47},{"id":"1504.02340","title":"Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor","created":"2015-04-09","cited_by_count":46},{"id":"2204.01586","title":"Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image","created":"2022-04-04","cited_by_count":30},{"id":"2008.08826","title":"Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking","created":"2020-08-20","cited_by_count":25},{"id":"2107.02396","title":"Semi-TCL: Semi-Supervised Track Contrastive Representation Learning","created":"2021-07-06","cited_by_count":23},{"id":"2203.10539","title":"End-to-End Video Text Spotting with Transformer","created":"2022-03-20","cited_by_count":22},{"id":"2101.04206","title":"TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking","created":"2021-01-11","cited_by_count":21},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21},{"id":"1901.06129","title":"Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification","created":"2019-01-18","cited_by_count":16}],"next_cursor":null}