{"url":"/task/multiple-object-tracking","name":"Multiple Object Tracking","slug":"multiple-object-tracking","description_markdown":"**Multiple Object Tracking** is the problem of automatically identifying multiple objects in a video and representing them as a set of trajectories with high accuracy.\n\n\n<span class=\"description-source\">Source: [SOT for MOT ](https://arxiv.org/abs/1712.01059)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":318,"papers_with_code":149,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":18,"subtasks":2,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/multiple-object-tracking-on-kitti-test-online","slug":"multiple-object-tracking-on-kitti-test-online","dataset":"KITTI Test (Online Methods)","dataset_url":"/dataset/kitti","rows_in_archive":34,"metrics":["HOTA","MOTA","IDSW"],"first_row_in_archive_order":{"model":"RobMOT (Dynamic)","paper_title":"Towards Accurate State Estimation: Kalman Filter Incorporating Motion Dynamics for 3D Multi-Object Tracking","paper_url":"/paper/towards-accurate-state-estimation-kalman","paper_date":"2025-05-12","arxiv_id":"2505.07254","code_links":[],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-sportsmot","slug":"multiple-object-tracking-on-sportsmot","dataset":"SportsMOT","dataset_url":"/dataset/sportsmot","rows_in_archive":19,"metrics":["HOTA","IDF1","AssA","MOTA","DetA"],"first_row_in_archive_order":{"model":"DeepEIoU + GTA","paper_title":"GTA: Global Tracklet Association for Multi-Object Tracking in Sports","paper_url":"/paper/gta-global-tracklet-association-for-multi","paper_date":"2024-11-12","arxiv_id":"2411.08216","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"}],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-bdd100k-val","slug":"multiple-object-tracking-on-bdd100k-val","dataset":"BDD100K val","dataset_url":"/dataset/bdd100k","rows_in_archive":9,"metrics":["mMOTA","mIDF1","TETA","AssocA"],"first_row_in_archive_order":{"model":"ByteTrack","paper_title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","paper_url":"/paper/bytetrack-multi-object-tracking-by-1","paper_date":"2021-10-13","arxiv_id":"2110.06864","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.3/configs/mot"},{"title":"mikel-brostrom/boxmot","url":"https://github.com/mikel-brostrom/boxmot"},{"title":"ifzhang/ByteTrack","url":"https://github.com/ifzhang/ByteTrack"},{"title":"kadirnar/bytetrack-pip","url":"https://github.com/kadirnar/bytetrack-pip"},{"title":"Robotmurlock/Motrack","url":"https://github.com/Robotmurlock/Motrack"},{"title":"wuhengliangliang/ByteTrack","url":"https://github.com/wuhengliangliang/ByteTrack"},{"title":"levinwil/MyteTrack","url":"https://github.com/levinwil/MyteTrack"},{"title":"levinwil/MulteTrack","url":"https://github.com/levinwil/MulteTrack"},{"title":"2023-MindSpore-1/ms-code-28","url":"https://github.com/2023-MindSpore-1/ms-code-28"},{"title":"HaojunYuPKU/MOT_detectron","url":"https://github.com/HaojunYuPKU/MOT_detectron"}],"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/multiple-object-tracking-on-bdd100k-test-1","slug":"multiple-object-tracking-on-bdd100k-test-1","dataset":"BDD100K test","dataset_url":"/dataset/bdd100k","rows_in_archive":5,"metrics":["mMOTA","mHOTA","mIDF1"],"first_row_in_archive_order":{"model":"ContrasTR","paper_title":"Contrastive Learning for Multi-Object Tracking with Transformers","paper_url":"/paper/contrastive-learning-for-multi-object","paper_date":"2023-11-14","arxiv_id":"2311.08043","code_links":[{"title":"pfdp0/ContrasTR","url":"https://github.com/pfdp0/ContrasTR"}],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-crohd","slug":"multiple-object-tracking-on-crohd","dataset":"CroHD","dataset_url":null,"rows_in_archive":5,"metrics":["MOTA","IDEucl","IDF1","IDs","ML","MT","HOTA"],"first_row_in_archive_order":{"model":"PP-Tracking","paper_title":"PP-YOLOE: An evolved version of YOLO","paper_url":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_date":"2022-03-30","arxiv_id":"2203.16250","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"Nioolek/PPYOLOE_pytorch","url":"https://github.com/Nioolek/PPYOLOE_pytorch"},{"title":"Gaurav14cs17/YOLOE","url":"https://github.com/Gaurav14cs17/YOLOE"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"2023-MindSpore-4/Code10","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/YOLOv5"},{"title":"Mind23-2/MindCode-130","url":"https://github.com/Mind23-2/MindCode-130"}],"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}}},{"leaderboard":"/sota/multiple-object-tracking-on-kitti-test","slug":"multiple-object-tracking-on-kitti-test","dataset":"KITTI Test (Offline Methods)","dataset_url":"/dataset/kitti","rows_in_archive":2,"metrics":["HOTA"],"first_row_in_archive_order":{"model":"MCTrack","paper_title":"MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving","paper_url":"/paper/mctrack-a-unified-3d-multi-object-tracking","paper_date":"2024-09-23","arxiv_id":"2409.16149","code_links":[{"title":"megvii-research/mctrack","url":"https://github.com/megvii-research/mctrack"}],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-radiate","slug":"multiple-object-tracking-on-radiate","dataset":"RADIATE","dataset_url":"/dataset/radiate","rows_in_archive":2,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"SIRA","paper_title":"SIRA: Scalable Inter-frame Relation and Association for Radar Perception","paper_url":"/paper/sira-scalable-inter-frame-relation-and-1","paper_date":"2024-11-04","arxiv_id":"2411.02220","code_links":[],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-waymo-open","slug":"multiple-object-tracking-on-waymo-open","dataset":"Waymo Open Dataset","dataset_url":"/dataset/waymo-open-dataset","rows_in_archive":2,"metrics":["Category","MOTA","mAP"],"first_row_in_archive_order":{"model":"QDTrack","paper_title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","paper_url":"/paper/quasi-dense-instance-similarity-learning","paper_date":"2020-06-11","arxiv_id":"2006.06664","code_links":[{"title":"SysCV/qdtrack","url":"https://github.com/SysCV/qdtrack"},{"title":"syscv/ovtrack","url":"https://github.com/syscv/ovtrack"},{"title":"SysCV/tet","url":"https://github.com/SysCV/tet"}],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-gmot-40","slug":"multiple-object-tracking-on-gmot-40","dataset":"GMOT-40","dataset_url":"/dataset/gmot-40","rows_in_archive":1,"metrics":["HOTA","IDF1","MOTA"],"first_row_in_archive_order":{"model":"MAC-SORT","paper_title":"TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT","paper_url":"/paper/tp-gmot-tracking-generic-multiple-object-by","paper_date":"2024-09-04","arxiv_id":"2409.02490","code_links":[{"title":"Fsoft-AIC/TP-GMOT","url":"https://github.com/Fsoft-AIC/TP-GMOT"}],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-ua-detrac","slug":"multiple-object-tracking-on-ua-detrac","dataset":"UA-DETRAC","dataset_url":"/dataset/ua-detrac","rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"EB & TADN","paper_title":"Transformer-based assignment decision network for multiple object tracking","paper_url":"/paper/transformer-based-assignment-decision-network","paper_date":"2022-08-06","arxiv_id":"2208.03571","code_links":[{"title":"psaltaath/tadn-mot","url":"https://github.com/psaltaath/tadn-mot"}],"syntology":null}},{"leaderboard":"/sota/multiple-object-tracking-on-youtube-hands","slug":"multiple-object-tracking-on-youtube-hands","dataset":"YouTube-Hands","dataset_url":"/dataset/youtube-hands","rows_in_archive":1,"metrics":["MOTA","HOTA"],"first_row_in_archive_order":{"model":"HandLer","paper_title":"Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild","paper_url":"/paper/forward-propagation-backward-regression-and","paper_date":"2022-01-01","arxiv_id":null,"code_links":[{"title":"cvlab-stonybrook/HandLer","url":"https://github.com/cvlab-stonybrook/HandLer"}],"syntology":null}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/waymo-open-dataset","name":"Waymo Open Dataset","full_name":"","num_papers_in_archive":481},{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/motchallenge","name":"MOTChallenge","full_name":"","num_papers_in_archive":192},{"url":"/dataset/ua-detrac","name":"UA-DETRAC","full_name":"","num_papers_in_archive":53},{"url":"/dataset/sportsmot","name":"SportsMOT","full_name":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","num_papers_in_archive":32},{"url":"/dataset/kitti-mots","name":"KITTI MOTS","full_name":"KITTI Multi-Object Tracking and Segmentation (MOTS) Evaluation","num_papers_in_archive":28},{"url":"/dataset/radiate","name":"RADIATE","full_name":"RAdar Dataset In Adverse weaThEr","num_papers_in_archive":24},{"url":"/dataset/hieve","name":"HiEve","full_name":"Human-in-Events","num_papers_in_archive":19},{"url":"/dataset/gmot-40","name":"GMOT-40","full_name":"Generic Multiple Object Tracking (GMOT)","num_papers_in_archive":12},{"url":"/dataset/pathtrack","name":"PathTrack","full_name":"","num_papers_in_archive":9},{"url":"/dataset/lpw","name":"LPW","full_name":"Labeled Pedestrian in the Wild","num_papers_in_archive":8},{"url":"/dataset/mmptrack","name":"MMPTRACK","full_name":"Multi-camera Multiple People Tracking Dataset","num_papers_in_archive":6},{"url":"/dataset/cfc","name":"CFC","full_name":"Caltech Fish Counting Dataset","num_papers_in_archive":3},{"url":"/dataset/personpath22","name":"PersonPath22","full_name":"","num_papers_in_archive":2},{"url":"/dataset/omni-mot","name":"Omni-MOT","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sompt22","name":"SOMPT22","full_name":"Surveillance Oriented Multi-Pedestrian Tracking Dataset (SOMPT22)","num_papers_in_archive":1},{"url":"/dataset/youtube-hands","name":"YouTube-Hands","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/multiple-object-track-and-segmentation","name":"Multiple Object Track and Segmentation"},{"url":"/task/multiple-object-tracking-with-transformer","name":"Multiple Object Tracking with Transformer"}],"parent_tasks":[{"url":"/task/object-tracking","name":"Object Tracking"},{"url":"/task/video","name":"Video"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":149,"tagged_in_all":318,"items":[{"url":"/paper/simple-online-and-realtime-tracking-with-a","title":"Simple Online and Realtime Tracking with a Deep Association Metric","date":"2017-03-21","arxiv_id":"1703.07402","repositories_listed":75,"syntology":{"n":40,"n_ran":12,"n_unverified":28,"n_pointer_only":7}},{"url":"/paper/simple-online-and-realtime-tracking","title":"Simple Online and Realtime Tracking","date":"2016-02-02","arxiv_id":"1602.00763","repositories_listed":56,"syntology":{"n":40,"n_ran":15,"n_unverified":25,"n_pointer_only":7}},{"url":"/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","arxiv_id":"2004.01888","repositories_listed":33,"syntology":{"n":53,"n_ran":8,"n_unverified":45,"n_pointer_only":0}},{"url":"/paper/towards-real-time-multi-object-tracking","title":"Towards Real-Time Multi-Object Tracking","date":"2019-09-27","arxiv_id":"1909.12605","repositories_listed":12,"syntology":{"n":36,"n_ran":2,"n_unverified":34,"n_pointer_only":0}},{"url":"/paper/bytetrack-multi-object-tracking-by-1","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","date":"2021-10-13","arxiv_id":"2110.06864","repositories_listed":10,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/pp-yoloe-an-evolved-version-of-yolo","title":"PP-YOLOE: An evolved version of YOLO","date":"2022-03-30","arxiv_id":"2203.16250","repositories_listed":8,"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/mot16-a-benchmark-for-multi-object-tracking","title":"MOT16: A Benchmark for Multi-Object Tracking","date":"2016-03-02","arxiv_id":"1603.00831","repositories_listed":8,"syntology":{"n":38,"n_ran":11,"n_unverified":27,"n_pointer_only":1}},{"url":"/paper/soccernet-2022-challenges-results","title":"SoccerNet 2022 Challenges Results","date":"2022-10-05","arxiv_id":"2210.02365","repositories_listed":7,"syntology":null},{"url":"/paper/observation-centric-sort-rethinking-sort-for","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","date":"2022-03-27","arxiv_id":"2203.14360","repositories_listed":7,"syntology":{"n":31,"n_ran":15,"n_unverified":16,"n_pointer_only":2}},{"url":"/paper/tracking-objects-as-points","title":"Tracking Objects as Points","date":"2020-04-02","arxiv_id":"2004.01177","repositories_listed":7,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/motrv2-bootstrapping-end-to-end-multi-object","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","date":"2022-11-17","arxiv_id":"2211.09791","repositories_listed":4,"syntology":null},{"url":"/paper/tracking-pedestrian-heads-in-dense-crowd","title":"Tracking Pedestrian Heads in Dense Crowd","date":"2021-03-24","arxiv_id":"2103.13516","repositories_listed":4,"syntology":null},{"url":"/paper/bdd100k-a-diverse-driving-video-database-with","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","date":"2018-05-12","arxiv_id":"1805.04687","repositories_listed":4,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/lucid-data-dreaming-for-video-object","title":"Lucid Data Dreaming for Video Object Segmentation","date":"2017-03-28","arxiv_id":"1703.09554","repositories_listed":4,"syntology":null},{"url":"/paper/the-1st-place-solution-for-eccv-2022-multiple","title":"The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge","date":"2022-10-27","arxiv_id":"2210.15281","repositories_listed":3,"syntology":null},{"url":"/paper/real-time-pear-fruit-detection-and-counting","title":"Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT","date":"2021-07-14","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/eagermot-3d-multi-object-tracking-via-sensor","title":"EagerMOT: 3D Multi-Object Tracking via Sensor Fusion","date":"2021-04-29","arxiv_id":"2104.14682","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/simultaneous-detection-and-tracking-with","title":"Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking","date":"2020-08-20","arxiv_id":"2008.08826","repositories_listed":3,"syntology":null},{"url":"/paper/quasi-dense-instance-similarity-learning","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","date":"2020-06-11","arxiv_id":"2006.06664","repositories_listed":3,"syntology":null},{"url":"/paper/gta-global-tracklet-association-for-multi","title":"GTA: Global Tracklet Association for Multi-Object Tracking in Sports","date":"2024-11-12","arxiv_id":"2411.08216","repositories_listed":2,"syntology":null},{"url":"/paper/when-to-extract-reid-features-a-selective","title":"When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking","date":"2024-09-10","arxiv_id":"2409.06617","repositories_listed":2,"syntology":null},{"url":"/paper/boosttrack-using-tracklet-information-to","title":"BoostTrack++: using tracklet information to detect more objects in multiple object tracking","date":"2024-08-23","arxiv_id":"2408.13003","repositories_listed":2,"syntology":null},{"url":"/paper/trackastra-transformer-based-cell-tracking","title":"Trackastra: Transformer-based cell tracking for live-cell microscopy","date":"2024-05-24","arxiv_id":"2405.15700","repositories_listed":2,"syntology":null},{"url":"/paper/soccernet-2023-challenges-results","title":"SoccerNet 2023 Challenges Results","date":"2023-09-12","arxiv_id":"2309.06006","repositories_listed":2,"syntology":null},{"url":"/paper/hybrid-sort-weak-cues-matter-for-online-multi","title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","date":"2023-08-01","arxiv_id":"2308.00783","repositories_listed":2,"syntology":null},{"url":"/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","arxiv_id":"2306.13074","repositories_listed":2,"syntology":null},{"url":"/paper/sparsetrack-multi-object-tracking-by","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","date":"2023-06-08","arxiv_id":"2306.05238","repositories_listed":2,"syntology":null},{"url":"/paper/smiletrack-similarity-learning-for-multiple","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","date":"2022-11-16","arxiv_id":"2211.08824","repositories_listed":2,"syntology":null},{"url":"/paper/qdtrack-quasi-dense-similarity-learning-for","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","date":"2022-10-12","arxiv_id":"2210.06984","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/dr-vic-decomposition-and-reasoning-for-video","title":"DR.VIC: Decomposition and Reasoning for Video Individual Counting","date":"2022-03-23","arxiv_id":"2203.12335","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":11}}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}