{"url":"/sota/multi-object-tracking-on-mot16","task":{"name":"Multi-Object Tracking","url":"/task/multi-object-tracking","note":null},"dataset":{"name":"MOT16","url":"/dataset/mot16"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Multi-Object Tracking** is a task in computer vision that involves detecting and tracking multiple objects within a video sequence. The goal is to identify and locate objects of interest in each frame and then associate them across frames to keep track of their movements over time. This task is challenging due to factors such as occlusion, motion blur, and changes in object appearance, and is typically solved using algorithms that integrate object detection and data association techniques.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["MOTA","IDF1","IDs"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MOTA":null,"IDF1":null,"IDs":null}},"counts":{"rows":24,"rows_with_code":18,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":8},"rows":[{"rank_in_archive_order":1,"model":"PPTracking","metrics":{"MOTA":"77.7"},"uses_additional_data":true,"paper_date":"2022-03-30","paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_url":"https://arxiv.org/abs/2203.16250v3","paper_title":"PP-YOLOE: An evolved version of YOLO","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":8,"syntology":{"n_ran":5,"n_unverified":22,"n_samples":27,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ReMOT","metrics":{"MOTA":"76.9"},"uses_additional_data":false,"paper_date":"2020-07-07","paper":"/paper/remots-self-supervised-refining-multi-object","paper_url":"https://arxiv.org/abs/2007.03200v3","paper_title":"ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SGT","metrics":{"IDF1":"73.5","MOTA":"76.8"},"uses_additional_data":true,"paper_date":"2022-05-02","paper":"/paper/detection-recovery-in-online-multi-object","paper_url":"https://arxiv.org/abs/2205.00968v3","paper_title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","code":"https://github.com/hyunjs/sgt","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"STGT","metrics":{"IDF1":"76.8","MOTA":"76.7"},"uses_additional_data":true,"paper_date":"2021-04-01","paper":"/paper/spatial-temporal-graph-transformer-for","paper_url":"https://arxiv.org/abs/2104.00194v2","paper_title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"FairMOT","metrics":{"MOTA":"74.9"},"uses_additional_data":true,"paper_date":"2020-04-04","paper":"/paper/a-simple-baseline-for-multi-object-tracking","paper_url":"https://arxiv.org/abs/2004.01888v6","paper_title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":33,"syntology":{"n_ran":8,"n_unverified":45,"n_samples":53,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"UniTrack","metrics":{"IDF1":"71.8","IDs":"683","MOTA":"74.7"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/do-different-tracking-tasks-require-different","paper_url":"https://arxiv.org/abs/2107.02156v2","paper_title":"Do Different Tracking Tasks Require Different Appearance Models?","code":"https://github.com/Zhongdao/UniTrack","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":11,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"OUTrack_fm","metrics":{"IDF1":"71.1","IDs":"1324","MOTA":"74.2"},"uses_additional_data":true,"paper_date":"2022-01-04","paper":"/paper/online-multi-object-tracking-with","paper_url":"https://arxiv.org/abs/2201.01297v1","paper_title":"Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"LMOT","metrics":{"IDF1":"72.3","IDs":"669","MOTA":"73.2"},"uses_additional_data":true,"paper_date":"2022-08-08","paper":"/paper/lmot-efficient-light-weight-detection-and","paper_url":"https://ieeexplore.ieee.org/document/9852199","paper_title":"LMOT: Efficient Light-Weight Detection and Tracking in Crowds","code":"https://github.com/RanaMostafaAbdElMohsen/LMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"TraDeS","metrics":{"IDF1":"64.7","MOTA":"70.1"},"uses_additional_data":true,"paper_date":"2021-03-16","paper":"/paper/track-to-detect-and-segment-an-online-multi","paper_url":"https://arxiv.org/abs/2103.08808v1","paper_title":"Track to Detect and Segment: An Online Multi-Object Tracker","code":"https://github.com/JialianW/TraDeS","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"QDTrack","metrics":{"IDF1":"67.1","MOTA":"69.8"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/quasi-dense-instance-similarity-learning","paper_url":"https://arxiv.org/abs/2006.06664v4","paper_title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","code":"https://github.com/SysCV/qdtrack","n_code_links":3,"syntology":null},{"rank_in_archive_order":11,"model":"DEFT","metrics":{"MOTA":"68.03"},"uses_additional_data":false,"paper_date":"2021-02-03","paper":"/paper/deft-detection-embeddings-for-tracking","paper_url":"https://arxiv.org/abs/2102.02267v2","paper_title":"DEFT: Detection Embeddings for Tracking","code":"https://github.com/MedChaabane/DEFT","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"MOTR","metrics":{"IDF1":"67.0","MOTA":"66.8"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/motr-end-to-end-multiple-object-tracking-with","paper_url":"https://arxiv.org/abs/2105.03247v4","paper_title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","code":"https://github.com/megvii-model/MOTR","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"GSDT","metrics":{"MOTA":"66.7"},"uses_additional_data":false,"paper_date":"2020-06-23","paper":"/paper/joint-detection-and-multi-object-tracking","paper_url":"https://arxiv.org/abs/2006.13164v3","paper_title":"Joint Object Detection and Multi-Object Tracking with Graph Neural Networks","code":"https://github.com/yongxinw/GSDT","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"JDE","metrics":{"MOTA":"64.4"},"uses_additional_data":true,"paper_date":"2019-09-27","paper":"/paper/towards-real-time-multi-object-tracking","paper_url":"https://arxiv.org/abs/1909.12605v2","paper_title":"Towards Real-Time Multi-Object Tracking","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":12,"syntology":{"n_ran":2,"n_unverified":34,"n_samples":36,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"HopTrack[Embedded GPU]","metrics":{"MOTA":"63.12"},"uses_additional_data":false,"paper_date":"2024-11-01","paper":"/paper/hoptrack-a-real-time-multi-object-tracking","paper_url":"https://arxiv.org/abs/2411.00608v1","paper_title":"HopTrack: A Real-time Multi-Object Tracking System for Embedded Devices","code":"https://github.com/Mrxiangli/HopTrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Lif_T","metrics":{"IDF1":"64.7","MOTA":"61.3"},"uses_additional_data":false,"paper_date":"2020-06-25","paper":"/paper/lifted-disjoint-paths-with-application-in-1","paper_url":"https://arxiv.org/abs/2006.14550v1","paper_title":"Lifted Disjoint Paths with Application in Multiple Object Tracking","code":"https://github.com/AndreaHor/LifT_Solver","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"MPNTrack","metrics":{"IDF1":"61.7","MOTA":"58.6"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/learning-a-neural-solver-for-multiple-object-1","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Braso_Learning_a_Neural_Solver_for_Multiple_Object_Tracking_CVPR_2020_paper.html","paper_title":"Learning a Neural Solver for Multiple Object Tracking","code":"https://github.com/dvl-tum/mot_neural_solver","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"DeepMOT-Tracktor","metrics":{"MOTA":"54.8"},"uses_additional_data":false,"paper_date":"2019-06-15","paper":"/paper/deepmot-a-differentiable-framework-for","paper_url":"https://arxiv.org/abs/1906.06618v3","paper_title":"How To Train Your Deep Multi-Object Tracker","code":"https://github.com/yihongXU/deepMOT","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"MOTDT","metrics":{"MOTA":"50.9"},"uses_additional_data":false,"paper_date":"2018-09-12","paper":"/paper/real-time-multiple-people-tracking-with","paper_url":"http://arxiv.org/abs/1809.04427v1","paper_title":"Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification","code":"https://github.com/longcw/MOTDT","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"TNT","metrics":{"MOTA":"49.2"},"uses_additional_data":false,"paper_date":"2018-11-18","paper":"/paper/exploit-the-connectivity-multi-object","paper_url":"http://arxiv.org/abs/1811.07258v1","paper_title":"Exploit the Connectivity: Multi-Object Tracking with TrackletNet","code":"https://github.com/GaoangW/TNT","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"GCRA","metrics":{"MOTA":"48.2"},"uses_additional_data":false,"paper_date":"2018-04-12","paper":"/paper/trajectory-factory-tracklet-cleaving-and-re","paper_url":"http://arxiv.org/abs/1804.04555v1","paper_title":"Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"FWT","metrics":{"MOTA":"47.8"},"uses_additional_data":false,"paper_date":"2017-05-23","paper":"/paper/fusion-of-head-and-full-body-detectors-for","paper_url":"http://arxiv.org/abs/1705.08314v4","paper_title":"Fusion of Head and Full-Body Detectors for Multi-Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"NOMT","metrics":{"MOTA":"46.4"},"uses_additional_data":false,"paper_date":"2015-04-09","paper":"/paper/near-online-multi-target-tracking-with","paper_url":"http://arxiv.org/abs/1504.02340v1","paper_title":"Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"DMMOT","metrics":{"MOTA":"46.1"},"uses_additional_data":false,"paper_date":"2019-02-02","paper":"/paper/online-multi-object-tracking-with-dual","paper_url":"http://arxiv.org/abs/1902.00749v1","paper_title":"Online Multi-Object Tracking with Dual Matching Attention Networks","code":"https://github.com/jizhu1023/DMAN_MOT","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":25,"n_unverified":118,"n_samples":143,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":25,"n_unverified":118,"n_samples":143,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}