{"url":"/sota/multi-object-tracking-on-sportsmot","task":{"name":"Multi-Object Tracking","url":"/task/multi-object-tracking","note":null},"dataset":{"name":"SportsMOT","url":"/dataset/sportsmot"},"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":["HOTA","IDF1","AssA","MOTA","DetA"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"HOTA":null,"IDF1":null,"AssA":null,"MOTA":null,"DetA":null}},"counts":{"rows":22,"rows_with_code":17,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":15},"rows":[{"rank_in_archive_order":1,"model":"DeepEIoU + GTA","metrics":{"AssA":"74.5","DetA":"88.2","HOTA":"81.0","IDF1":"86.5","MOTA":"96.3"},"uses_additional_data":true,"paper_date":"2024-11-12","paper":"/paper/gta-global-tracklet-association-for-multi","paper_url":"https://arxiv.org/abs/2411.08216v1","paper_title":"GTA: Global Tracklet Association for Multi-Object Tracking in Sports","code":"https://github.com/sjc042/gta-link","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"HAT-FastReID-MOT","metrics":{"AssA":"73.1","DetA":"89.4","HOTA":"80.8","IDF1":"84.7"},"uses_additional_data":true,"paper_date":"2025-03-16","paper":"/paper/history-aware-transformation-of-reid-features","paper_url":"https://arxiv.org/abs/2503.12562v1","paper_title":"History-Aware Transformation of ReID Features for Multiple Object Tracking","code":"https://github.com/HELLORPG/HATReID-MOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CAMELTrack (fully online)","metrics":{"AssA":"72.8","DetA":"88.8","HOTA":"80.4","IDF1":"84.8","MOTA":"96.3"},"uses_additional_data":false,"paper_date":"2025-05-02","paper":"/paper/cameltrack-context-aware-multi-cue-1","paper_url":"https://arxiv.org/abs/2505.01257v1","paper_title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","code":"https://github.com/TrackingLaboratory/CAMELTrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Deep HM-SORT","metrics":{"AssA":"72.7","DetA":"88.3","HOTA":"80.1","IDF1":"85.2","MOTA":"96.6"},"uses_additional_data":true,"paper_date":"2024-06-17","paper":"/paper/deep-hm-sort-enhancing-multi-object-tracking","paper_url":"https://arxiv.org/abs/2406.12081v1","paper_title":"Deep HM-SORT: Enhancing Multi-Object Tracking in Sports with Deep Features, Harmonic Mean, and Expansion IOU","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"AED","metrics":{"AssA":"70.1","DetA":"89.4","HOTA":"79.1","IDF1":"81.8","MOTA":"97.1"},"uses_additional_data":true,"paper_date":"2024-09-14","paper":"/paper/associate-everything-detected-facilitating","paper_url":"https://arxiv.org/abs/2409.09293v1","paper_title":"Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown","code":"https://github.com/balabooooo/aed","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DeepMoveSORT","metrics":{"AssA":"70.3","DetA":"88.1","HOTA":"78.7","IDF1":"81.7","MOTA":"96.5"},"uses_additional_data":true,"paper_date":"2024-06-30","paper":"/paper/engineering-an-efficient-object-tracker-for-1","paper_url":"https://arxiv.org/abs/2407.00738v1","paper_title":"Engineering an Efficient Object Tracker for Non-Linear Motion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Deep-EIoU","metrics":{"AssA":"67.7","DetA":"88.2","HOTA":"77.2","IDF1":"79.8","MOTA":"96.3"},"uses_additional_data":true,"paper_date":"2023-06-22","paper":"/paper/iterative-scale-up-expansioniou-and-deep","paper_url":"https://arxiv.org/abs/2306.13074v5","paper_title":"Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports","code":"https://github.com/hsiangwei0903/Deep-EIoU","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"MoveSORT","metrics":{"AssA":"63.7","DetA":"87.5","HOTA":"74.6","IDF1":"76.9","MOTA":"96.7"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/beyond-kalman-filters-deep-learning-based","paper_url":"https://arxiv.org/abs/2402.09865v1","paper_title":"Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking","code":"https://github.com/Robotmurlock/NODETracker","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"ETTrack","metrics":{"AssA":"62.1","DetA":"88.8","HOTA":"74.3","IDF1":"74.5","MOTA":"96.8"},"uses_additional_data":false,"paper_date":"2024-05-24","paper":"/paper/ettrack-enhanced-temporal-motion-predictor","paper_url":"https://arxiv.org/abs/2405.15755v1","paper_title":"ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"MixSort-OC","metrics":{"AssA":"62.0","DetA":"88.5","HOTA":"74.1","IDF1":"74.4","MOTA":"96.5"},"uses_additional_data":true,"paper_date":"2023-04-11","paper":"/paper/sportsmot-a-large-multi-object-tracking","paper_url":"https://arxiv.org/abs/2304.05170v2","paper_title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","code":"https://github.com/MCG-NJU/SportsMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"MotionTrack","metrics":{"AssA":"61.7","DetA":"88.8","HOTA":"74.0","IDF1":"74.0","MOTA":"96.6"},"uses_additional_data":false,"paper_date":"2023-06-05","paper":"/paper/motiontrack-learning-motion-predictor-for","paper_url":"https://arxiv.org/abs/2306.02585v2","paper_title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"OC-SORT","metrics":{"AssA":"61.5","DetA":"88.5","HOTA":"73.7","IDF1":"74.0","MOTA":"96.5"},"uses_additional_data":true,"paper_date":"2022-03-27","paper":"/paper/observation-centric-sort-rethinking-sort-for","paper_url":"https://arxiv.org/abs/2203.14360v3","paper_title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":7,"syntology":{"n_ran":23,"n_unverified":8,"n_samples":31,"n_pointer_only_licence":2}},{"rank_in_archive_order":13,"model":"MambaMOT","metrics":{"AssA":"58.6","DetA":"86.7","HOTA":"71.3","IDF1":"71.1","MOTA":"94.9"},"uses_additional_data":true,"paper_date":"2024-03-16","paper":"/paper/exploring-learning-based-motion-models-in","paper_url":"https://arxiv.org/abs/2403.10826v2","paper_title":"MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"MeMOTR","metrics":{"AssA":"59.1","DetA":"83.1","HOTA":"70.0","IDF1":"71.4","MOTA":"91.5"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/memotr-long-term-memory-augmented-transformer","paper_url":"https://arxiv.org/abs/2307.15700v3","paper_title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","code":"https://github.com/mcg-nju/memotr","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"TransTrack","metrics":{"AssA":"57.5","DetA":"82.7","HOTA":"68.9","IDF1":"71.5","MOTA":"92.6"},"uses_additional_data":true,"paper_date":"2020-12-31","paper":"/paper/transtrack-multiple-object-tracking-with","paper_url":"https://arxiv.org/abs/2012.15460v2","paper_title":"TransTrack: Multiple Object Tracking with Transformer","code":"https://github.com/PeizeSun/TransTrack","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"MeMOTR (Deformable-DETR)","metrics":{"AssA":"57.8","DetA":"82.0","HOTA":"68.8","IDF1":"69.9","MOTA":"90.2"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/memotr-long-term-memory-augmented-transformer","paper_url":"https://arxiv.org/abs/2307.15700v3","paper_title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","code":"https://github.com/mcg-nju/memotr","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"MixSort-Byte","metrics":{"AssA":"54.8","DetA":"78.8","HOTA":"65.7","IDF1":"74.1","MOTA":"96.2"},"uses_additional_data":true,"paper_date":"2023-04-11","paper":"/paper/sportsmot-a-large-multi-object-tracking","paper_url":"https://arxiv.org/abs/2304.05170v2","paper_title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","code":"https://github.com/MCG-NJU/SportsMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"ByteTrack","metrics":{"AssA":"52.3","DetA":"78.5","HOTA":"64.1","IDF1":"71.4","MOTA":"95.9"},"uses_additional_data":true,"paper_date":"2021-10-13","paper":"/paper/bytetrack-multi-object-tracking-by-1","paper_url":"https://arxiv.org/abs/2110.06864v3","paper_title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","code":"https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.3/configs/mot","n_code_links":10,"syntology":{"n_ran":8,"n_unverified":4,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"CenterTrack","metrics":{"AssA":"48.0","DetA":"82.1","HOTA":"62.7","IDF1":"60.0","MOTA":"90.8"},"uses_additional_data":true,"paper_date":"2020-04-02","paper":"/paper/tracking-objects-as-points","paper_url":"https://arxiv.org/abs/2004.01177v2","paper_title":"Tracking Objects as Points","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":7,"syntology":{"n_ran":10,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"QDTrack","metrics":{"AssA":"47.2","DetA":"77.5","HOTA":"60.4","IDF1":"62.3","MOTA":"90.1"},"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":21,"model":"GTR","metrics":{"AssA":"45.9","DetA":"64.8","HOTA":"54.5","IDF1":"55.8","MOTA":"67.9"},"uses_additional_data":true,"paper_date":"2022-03-24","paper":"/paper/global-tracking-transformers","paper_url":"https://arxiv.org/abs/2203.13250v2","paper_title":"Global Tracking Transformers","code":"https://github.com/xingyizhou/GTR","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":22,"model":"FairMOT","metrics":{"AssA":"34.7","DetA":"70.2","HOTA":"49.3","IDF1":"53.5","MOTA":"86.4"},"uses_additional_data":false,"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":39,"n_unverified":14,"n_samples":53,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":94,"n_unverified":37,"n_samples":131,"n_pointer_only_licence":7,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":104,"n_unverified":41,"n_samples":145,"n_pointer_only_licence":7,"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"}}}