{"url":"/dataset/sportsmot","name":"SportsMOT","full_name":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","description_markdown":"## Motivation\r\n\r\nMulti-object tracking (MOT) is a fundamental task in computer vision, aiming to estimate objects (e.g., pedestrians and vehicles) bounding boxes and identities in video sequences.\r\n\r\nPrevailing human-tracking MOT datasets mainly focus on pedestrians in crowded street scenes (e.g., [MOT17](https://motchallenge.net/data/MOT17/)/[20](https://motchallenge.net/data/MOT20/)) or dancers in static scenes ([DanceTrack](https://github.com/DanceTrack/DanceTrack)). \r\n\r\nIn spite of the increasing demands for sports analysis, there is a lack of multi-object tracking datasets for a variety of **sports scenes**, where the background is complicated, players possess rapid motion and the camera lens moves fast.\r\n\r\nTo this purpose, we propose a large-scale multi-object tracking dataset named SportsMOT, consisting of **240 video** clips from **3 categories** (i.e., basketball, football and volleyball). \r\n\r\nThe objective is to only track players on the playground (i.e., except for a number of spectators, referees and coaches) in various sports scenes. We expect SportsMOT to encourage the community to concentrate more on the complicated sports scenes.\r\n\r\n## Characteristics\r\n\r\n- Large scale\r\n- Fine Annotations\r\n- Player id consistency\r\n- No shot change\r\n- High and fixed resolution(1080P)\r\n- ...\r\n\r\n## Focus\r\n\r\n- Diverse sports **scenes**\r\n- Complex **motion** patterns\r\n- Challenging **re-id**\r\n\r\n## Download\r\n\r\n### Examples\r\n\r\nYou can download the example for SportsMOT.\r\n\r\n- [OneDrive](https://1drv.ms/u/s!AtjeLq7YnYGRgQRrmqGr4B-k-xsC?e=7PndU8)\r\n- [Baidu Netdisk](https://pan.baidu.com/s/1gytkTngxoGFlmP9_DBd1xw), password: 4dnw\r\n\r\n### Official Dataset\r\n\r\nPlease Sign up in codalab, and participate in our [competition](https://codalab.lisn.upsaclay.fr/competitions/12424). Download links are available in  `Participate`/`Get Data`.\r\n\r\n## News\r\n\r\n- SportsMOT is used for  [DeeperAction@ECCV-2022](https://deeperaction.github.io/tracks/sportsmot.html). \r\n\r\n- Refer to github repo: [MCG-NJU/SportsMOT](https://github.com/MCG-NJU/SportsMOT) for the latest info.","description_withheld":null,"homepage":"https://github.com/MCG-NJU/SportsMOT","introduced_date":"2023-04-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/sportsmot-a-large-multi-object-tracking","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","first_author":"Yutao Cui","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Multi-Object Tracking","url":"/task/multi-object-tracking","datasets_with_task":"/datasets/task/multi-object-tracking"},{"name":"Multiple Object Tracking","url":"/task/multiple-object-tracking","datasets_with_task":"/datasets/task/multiple-object-tracking"},{"name":"Online Multi-Object Tracking","url":"/task/online-multi-object-tracking","datasets_with_task":"/datasets/task/online-multi-object-tracking"}],"languages":[],"variants":["SportsMOT"],"data_loaders":[],"num_papers_in_archive":32,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-object-tracking-on-sportsmot","task":"Multi-Object Tracking","dataset_variant":"SportsMOT","rows":22,"metrics":["HOTA","IDF1","AssA","MOTA","DetA"],"first_row_in_archive_order":{"model":"DeepEIoU + GTA","paper":"/paper/gta-global-tracklet-association-for-multi","metrics":{"AssA":"74.5","DetA":"88.2","HOTA":"81.0","IDF1":"86.5","MOTA":"96.3"},"code_links":[{"title":"sjc042/gta-link","url":"https://github.com/sjc042/gta-link"},{"title":"zakroum-hicham/gta-DeepEIou-YOLO","url":"https://github.com/zakroum-hicham/gta-DeepEIou-YOLO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-object-tracking-on-sportsmot","task":"Multiple Object Tracking","dataset_variant":"SportsMOT","rows":19,"metrics":["HOTA","IDF1","AssA","MOTA","DetA"],"first_row_in_archive_order":{"model":"DeepEIoU + GTA","paper":"/paper/gta-global-tracklet-association-for-multi","metrics":{"AssA":"74.5","DetA":"88.2","HOTA":"81.0","IDF1":"86.5","MOTA":"96.3"},"code_links":[{"title":"sjc042/gta-link","url":"https://github.com/sjc042/gta-link"},{"title":"zakroum-hicham/gta-DeepEIou-YOLO","url":"https://github.com/zakroum-hicham/gta-DeepEIou-YOLO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/online-multi-object-tracking-on-sportsmot","task":"Online Multi-Object Tracking","dataset_variant":"SportsMOT","rows":1,"metrics":["HOTA"],"first_row_in_archive_order":{"model":"CAMELTrack","paper":"/paper/cameltrack-context-aware-multi-cue-1","metrics":{"HOTA":"80.4"},"code_links":[{"title":"TrackingLaboratory/CAMELTrack","url":"https://github.com/TrackingLaboratory/CAMELTrack"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cameltrack-context-aware-multi-cue-1","title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","date":"2025-05-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/history-aware-transformation-of-reid-features","title":"History-Aware Transformation of ReID Features for Multiple Object Tracking","date":"2025-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gta-global-tracklet-association-for-multi","title":"GTA: Global Tracklet Association for Multi-Object Tracking in Sports","date":"2024-11-12","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/associate-everything-detected-facilitating","title":"Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown","date":"2024-09-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/trackssm-a-general-motion-predictor-by-state","title":"TrackSSM: A General Motion Predictor by State-Space Model","date":"2024-08-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/engineering-an-efficient-object-tracker-for-1","title":"Engineering an Efficient Object Tracker for Non-Linear Motion","date":"2024-06-30","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/deep-hm-sort-enhancing-multi-object-tracking","title":"Deep HM-SORT: Enhancing Multi-Object Tracking in Sports with Deep Features, Harmonic Mean, and Expansion IOU","date":"2024-06-17","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/ettrack-enhanced-temporal-motion-predictor","title":"ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Tracking","date":"2024-05-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multiple-object-tracking-as-id-prediction","title":"Multiple Object Tracking as ID Prediction","date":"2024-03-25","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-learning-based-motion-models-in","title":"MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking","date":"2024-03-16","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/beyond-kalman-filters-deep-learning-based","title":"Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking","date":"2024-02-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/memotr-long-term-memory-augmented-transformer","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","date":"2023-07-28","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":10,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/iterative-scale-up-expansioniou-and-deep","title":"Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports","date":"2023-06-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/motiontrack-learning-motion-predictor-for","title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","date":"2023-06-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sportsmot-a-large-multi-object-tracking","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","date":"2023-04-11","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/observation-centric-sort-rethinking-sort-for","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","date":"2022-03-27","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":15,"samples_unverified":16,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/global-tracking-transformers","title":"Global Tracking Transformers","date":"2022-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bytetrack-multi-object-tracking-by-1","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","date":"2021-10-13","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":1,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transtrack-multiple-object-tracking-with","title":"TransTrack: Multiple Object Tracking with Transformer","date":"2020-12-31","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/quasi-dense-instance-similarity-learning","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","date":"2020-06-11","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/a-simple-baseline-for-multi-object-tracking","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","date":"2020-04-04","rows_on_this_dataset":2,"code_links":33,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":53,"samples_ran":8,"samples_unverified":45,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tracking-objects-as-points","title":"Tracking Objects as Points","date":"2020-04-02","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":4,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":7,"samples_harvested":141,"samples_ran":52,"samples_unverified":89,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}