{"url":"/task/online-multi-object-tracking","name":"Online Multi-Object Tracking","slug":"online-multi-object-tracking","description_markdown":"The goal of **Online Multi-Object Tracking** is to estimate the spatio-temporal trajectories of multiple objects in an online video stream (i.e., the video is provided frame-by-frame), which is a fundamental problem for numerous real-time applications, such as video surveillance, autonomous driving, and robot navigation.\r\n\r\n\r\n<span class=\"description-source\">Source: [A Hybrid Data Association Framework for Robust Online Multi-Object Tracking ](https://arxiv.org/abs/1703.10764)</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":56,"papers_with_code":30,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":10,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/online-multi-object-tracking-on-mot16","slug":"online-multi-object-tracking-on-mot16","dataset":"MOT16","dataset_url":"/dataset/mot16","rows_in_archive":5,"metrics":["MOTA"],"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/online-multi-object-tracking-on-mot17","slug":"online-multi-object-tracking-on-mot17","dataset":"MOT17","dataset_url":"/dataset/mot17","rows_in_archive":2,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"Tracktor++","paper_title":"Tracking without bells and whistles","paper_url":"/paper/tracking-without-bells-and-whistles","paper_date":"2019-03-13","arxiv_id":"1903.05625","code_links":[{"title":"phil-bergmann/tracking_wo_bnw","url":"https://github.com/phil-bergmann/tracking_wo_bnw"},{"title":"dvl-tum/mot_neural_solver","url":"https://github.com/dvl-tum/mot_neural_solver"},{"title":"mhnasseri/sort_oh","url":"https://github.com/mhnasseri/sort_oh"},{"title":"dvl-tum/motsynth-baselines","url":"https://github.com/dvl-tum/motsynth-baselines"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/rbpn"},{"title":"a-doering/tracker_w_correlation_motion_model","url":"https://github.com/a-doering/tracker_w_correlation_motion_model"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tracktor"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tracktor%2B%2B"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/tracktor%2B%2B"},{"title":"MkuuWaUjinga/Self-Supervised-Learning-for-Tracktor","url":"https://github.com/MkuuWaUjinga/Self-Supervised-Learning-for-Tracktor"},{"title":"LKLQQ/tracktor","url":"https://github.com/LKLQQ/tracktor"},{"title":"MindSpore-paper-code-2/code3","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/tracktor%2B%2B"},{"title":"HoganZhang/mot_neural_solver","url":"https://github.com/HoganZhang/mot_neural_solver"}],"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":2}}},{"leaderboard":"/sota/online-multi-object-tracking-on-2d-mot-2015","slug":"online-multi-object-tracking-on-2d-mot-2015","dataset":"2D MOT 2015","dataset_url":"/dataset/mot15","rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"Tracktor++","paper_title":"Tracking without bells and whistles","paper_url":"/paper/tracking-without-bells-and-whistles","paper_date":"2019-03-13","arxiv_id":"1903.05625","code_links":[{"title":"phil-bergmann/tracking_wo_bnw","url":"https://github.com/phil-bergmann/tracking_wo_bnw"},{"title":"dvl-tum/mot_neural_solver","url":"https://github.com/dvl-tum/mot_neural_solver"},{"title":"mhnasseri/sort_oh","url":"https://github.com/mhnasseri/sort_oh"},{"title":"dvl-tum/motsynth-baselines","url":"https://github.com/dvl-tum/motsynth-baselines"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/rbpn"},{"title":"a-doering/tracker_w_correlation_motion_model","url":"https://github.com/a-doering/tracker_w_correlation_motion_model"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tracktor"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tracktor%2B%2B"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/tracktor%2B%2B"},{"title":"MkuuWaUjinga/Self-Supervised-Learning-for-Tracktor","url":"https://github.com/MkuuWaUjinga/Self-Supervised-Learning-for-Tracktor"},{"title":"LKLQQ/tracktor","url":"https://github.com/LKLQQ/tracktor"},{"title":"MindSpore-paper-code-2/code3","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/tracktor%2B%2B"},{"title":"HoganZhang/mot_neural_solver","url":"https://github.com/HoganZhang/mot_neural_solver"}],"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":2}}},{"leaderboard":"/sota/online-multi-object-tracking-on-mot15","slug":"online-multi-object-tracking-on-mot15","dataset":"MOT15","dataset_url":"/dataset/mot15","rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"GMPHD Filter (Occlusion Group Management)","paper_title":"Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management","paper_url":"/paper/online-multi-object-tracking-framework-with","paper_date":"2019-07-31","arxiv_id":"1907.13347","code_links":[{"title":"SonginCV/GMPHD-OGM_Tracker","url":"https://github.com/SonginCV/GMPHD-OGM_Tracker"},{"title":"SonginCV/MAF_HDA","url":"https://github.com/SonginCV/MAF_HDA"}],"syntology":null}},{"leaderboard":"/sota/online-multi-object-tracking-on-oxford-town","slug":"online-multi-object-tracking-on-oxford-town","dataset":"Oxford Town Center","dataset_url":"/dataset/oxford-town-center","rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"RCMSS","paper_title":"Online multi-object tracking via robust collaborative model and sample selection","paper_url":"/paper/online-multi-object-tracking-via-robust","paper_date":"2017-01-01","arxiv_id":null,"code_links":[{"title":"MNaiel/rcmss","url":"https://github.com/MNaiel/rcmss"}],"syntology":null}},{"leaderboard":"/sota/online-multi-object-tracking-on-sportsmot","slug":"online-multi-object-tracking-on-sportsmot","dataset":"SportsMOT","dataset_url":"/dataset/sportsmot","rows_in_archive":1,"metrics":["HOTA"],"first_row_in_archive_order":{"model":"CAMELTrack","paper_title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","paper_url":"/paper/cameltrack-context-aware-multi-cue-1","paper_date":"2025-05-02","arxiv_id":"2505.01257","code_links":[{"title":"TrackingLaboratory/CAMELTrack","url":"https://github.com/TrackingLaboratory/CAMELTrack"}],"syntology":null}}],"datasets":[{"url":"/dataset/mot17","name":"MOT17","full_name":"Multiple Object Tracking 17","num_papers_in_archive":291},{"url":"/dataset/motchallenge","name":"MOTChallenge","full_name":"","num_papers_in_archive":192},{"url":"/dataset/mot16","name":"MOT16","full_name":"Multiple Object Tracking 2016","num_papers_in_archive":149},{"url":"/dataset/mot15","name":"MOT15","full_name":"Multiple Object Tracking 15","num_papers_in_archive":67},{"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/mmptrack","name":"MMPTRACK","full_name":"Multi-camera Multiple People Tracking Dataset","num_papers_in_archive":6},{"url":"/dataset/bee23","name":"BEE23","full_name":"Multi-bee Tracking Benchmark","num_papers_in_archive":2},{"url":"/dataset/cholectrack20","name":"CholecTrack20","full_name":"Multi-Perspective Multi-Class Multi-Object Tracking Dataset For Surgical Tools","num_papers_in_archive":2},{"url":"/dataset/personpath22","name":"PersonPath22","full_name":"","num_papers_in_archive":2},{"url":"/dataset/oxford-town-center","name":"Oxford Town Center","full_name":"Oxford Town Center","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/object-tracking","name":"Object Tracking"}],"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":30,"tagged_in_all":56,"items":[{"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/real-time-multiple-people-tracking-with","title":"Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification","date":"2018-09-12","arxiv_id":"1809.04427","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/no-blind-spots-full-surround-multi-object","title":"No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs","date":"2018-02-23","arxiv_id":"1802.08755","repositories_listed":3,"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/large-scale-pre-training-for-person-re","title":"Large-Scale Pre-training for Person Re-identification with Noisy Labels","date":"2022-03-30","arxiv_id":"2203.16533","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/gcnnmatch-graph-convolutional-neural-networks","title":"GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization","date":"2020-09-30","arxiv_id":"2010.00067","repositories_listed":2,"syntology":null},{"url":"/paper/online-multi-object-tracking-framework-with","title":"Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management","date":"2019-07-31","arxiv_id":"1907.13347","repositories_listed":2,"syntology":null},{"url":"/paper/focusing-on-tracks-for-online-multi-object","title":"Focusing on Tracks for Online Multi-Object Tracking","date":"2025-06-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cameltrack-context-aware-multi-cue-1","title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","date":"2025-05-02","arxiv_id":"2505.01257","repositories_listed":1,"syntology":null},{"url":"/paper/lost-and-found-overcoming-detector-failures","title":"Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking","date":"2024-07-14","arxiv_id":"2407.10151","repositories_listed":1,"syntology":null},{"url":"/paper/putr-a-pure-transformer-for-decoupled-and","title":"PuTR: A Pure Transformer for Decoupled and Online Multi-Object Tracking","date":"2024-05-23","arxiv_id":"2405.14119","repositories_listed":1,"syntology":null},{"url":"/paper/sfsort-scene-features-based-simple-online","title":"SFSORT: Scene Features-based Simple Online Real-Time Tracker","date":"2024-04-11","arxiv_id":"2404.07553","repositories_listed":1,"syntology":null},{"url":"/paper/detection-recovery-in-online-multi-object","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","date":"2022-05-02","arxiv_id":"2205.00968","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-online-multi-object-tracking-in","title":"Real-time Online Multi-Object Tracking in Compressed Domain","date":"2022-04-05","arxiv_id":"2204.02081","repositories_listed":1,"syntology":null},{"url":"/paper/do-different-tracking-tasks-require-different","title":"Do Different Tracking Tasks Require Different Appearance Models?","date":"2021-07-05","arxiv_id":"2107.02156","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/siammot-siamese-multi-object-tracking","title":"SiamMOT: Siamese Multi-Object Tracking","date":"2021-05-25","arxiv_id":"2105.11595","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learnable-graph-matching-incorporating-graph","title":"Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking","date":"2021-03-30","arxiv_id":"2103.16178","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":12}},{"url":"/paper/looking-beyond-two-frames-end-to-end-multi","title":"Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers","date":"2021-03-27","arxiv_id":"2103.14829","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-track-with-object-permanence","title":"Learning to Track with Object Permanence","date":"2021-03-26","arxiv_id":"2103.14258","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/track-to-detect-and-segment-an-online-multi","title":"Track to Detect and Segment: An Online Multi-Object Tracker","date":"2021-03-16","arxiv_id":"2103.08808","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/online-multi-object-tracking-and-segmentation","title":"Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion","date":"2020-08-31","arxiv_id":"2009.00100","repositories_listed":1,"syntology":null},{"url":"/paper/segment-as-points-for-efficient-online-multi","title":"Segment as Points for Efficient Online Multi-Object Tracking and Segmentation","date":"2020-07-03","arxiv_id":"2007.01550","repositories_listed":1,"syntology":null},{"url":"/paper/pointtrack-for-effective-online-multi-object","title":"PointTrack++ for Effective Online Multi-Object Tracking and Segmentation","date":"2020-07-03","arxiv_id":"2007.01549","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-object-motion-and-affinity-model","title":"A Unified Object Motion and Affinity Model for Online Multi-Object Tracking","date":"2020-03-25","arxiv_id":"2003.11291","repositories_listed":1,"syntology":null},{"url":"/paper/fantrack-3d-multi-object-tracking-with","title":"FANTrack: 3D Multi-Object Tracking with Feature Association Network","date":"2019-05-07","arxiv_id":"1905.02843","repositories_listed":1,"syntology":null},{"url":"/paper/online-multi-object-tracking-with-dual","title":"Online Multi-Object Tracking with Dual Matching Attention Networks","date":"2019-02-02","arxiv_id":"1902.00749","repositories_listed":1,"syntology":null},{"url":"/paper/joint-monocular-3d-vehicle-detection-and","title":"Joint Monocular 3D Vehicle Detection and Tracking","date":"2018-11-26","arxiv_id":"1811.10742","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/tracking-by-animation-unsupervised-learning","title":"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers","date":"2018-09-10","arxiv_id":"1809.03137","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-pixels-leveraging-geometry-and-shape","title":"Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking","date":"2018-02-26","arxiv_id":"1802.09298","repositories_listed":1,"syntology":null},{"url":"/paper/online-multi-object-tracking-via-robust","title":"Online multi-object tracking via robust collaborative model and sample selection","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}