{"url":"/sota/multiple-object-tracking-on-kitti-test-online","task":{"name":"Multiple Object Tracking","url":"/task/multiple-object-tracking","note":null},"dataset":{"name":"KITTI Test (Online Methods)","url":"/dataset/kitti"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**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>","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","MOTA","IDSW"],"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,"MOTA":null,"IDSW":null}},"counts":{"rows":34,"rows_with_code":18,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RobMOT (Dynamic)","metrics":{"HOTA":"81.80","IDSW":"13","MOTA":"91.11"},"uses_additional_data":false,"paper_date":"2025-05-12","paper":"/paper/towards-accurate-state-estimation-kalman","paper_url":"https://arxiv.org/abs/2505.07254v1","paper_title":"Towards Accurate State Estimation: Kalman Filter Incorporating Motion Dynamics for 3D Multi-Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"RobMOT","metrics":{"HOTA":"81.76","IDSW":"7","MOTA":"91.02"},"uses_additional_data":false,"paper_date":"2024-05-19","paper":"/paper/robmot-robust-3d-multi-object-tracking-by","paper_url":"https://arxiv.org/abs/2405.11536v4","paper_title":"RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloud","code":"https://github.com/MohamedNagyMostafa/RobMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MCTrack","metrics":{"HOTA":"81.07","IDSW":"64","MOTA":"89.82"},"uses_additional_data":false,"paper_date":"2024-09-23","paper":"/paper/mctrack-a-unified-3d-multi-object-tracking","paper_url":"https://arxiv.org/abs/2409.16149v2","paper_title":"MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving","code":"https://github.com/megvii-research/mctrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"KFDL","metrics":{"HOTA":"81.06","IDSW":"22","MOTA":"90.29"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"PC-TCNN","metrics":{"HOTA":"80.90","IDSW":"37","MOTA":"78.46"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"LEGO","metrics":{"HOTA":"80.75","IDSW":"214","MOTA":"90.61"},"uses_additional_data":false,"paper_date":"2023-08-19","paper":"/paper/lego-learning-and-graph-optimized-modular","paper_url":"https://arxiv.org/abs/2308.09908v4","paper_title":"LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"VirConvTrack","metrics":{"HOTA":"79.9","IDSW":"201","MOTA":"89.1"},"uses_additional_data":false,"paper_date":"2023-03-04","paper":"/paper/virtual-sparse-convolution-for-multimodal-3d","paper_url":"https://arxiv.org/abs/2303.02314v1","paper_title":"Virtual Sparse Convolution for Multimodal 3D Object Detection","code":"https://github.com/hailanyi/virconv","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"IMM-JHSE","metrics":{"HOTA":"79.21","IDSW":"177","MOTA":"89.8"},"uses_additional_data":false,"paper_date":"2024-09-04","paper":"/paper/interacting-multiple-model-based-joint","paper_url":"https://arxiv.org/abs/2409.02562v3","paper_title":"One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation","code":"https://github.com/Paulkie99/imm-jhse","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"C-TWiX","metrics":{"HOTA":"77.58","IDSW":"381","MOTA":"89.68"},"uses_additional_data":false,"paper_date":"2024-03-12","paper":"/paper/learning-data-association-for-multi-object","paper_url":"https://arxiv.org/abs/2403.08018v1","paper_title":"Learning Data Association for Multi-Object Tracking using Only Coordinates","code":"https://github.com/Guepardow/TWiX","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CasTrack","metrics":{"HOTA":"77.3","IDSW":"184","MOTA":"86,29"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"UCMCTrack","metrics":{"HOTA":"77.1","MOTA":"90.4"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/ucmctrack-multi-object-tracking-with-uniform","paper_url":"https://arxiv.org/abs/2312.08952v2","paper_title":"UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation","code":"https://github.com/corfyi/ucmctrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"OC-SORT","metrics":{"HOTA":"76.5","IDSW":"250","MOTA":"90.3"},"uses_additional_data":false,"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":15,"n_unverified":16,"n_samples":31,"n_pointer_only_licence":2}},{"rank_in_archive_order":13,"model":"EagerMOT","metrics":{"HOTA":"74.39","IDSW":"239","MOTA":"87.82"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/eagermot-3d-multi-object-tracking-via-sensor","paper_url":"https://arxiv.org/abs/2104.14682v1","paper_title":"EagerMOT: 3D Multi-Object Tracking via Sensor Fusion","code":"https://github.com/aleksandrkim61/EagerMOT","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"DEFT","metrics":{"HOTA":"74.23 ","MOTA":"88.95"},"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":15,"model":"CenterTrack","metrics":{"HOTA":"73.02","MOTA":"89.44"},"uses_additional_data":false,"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":4,"n_unverified":12,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"QD-3DT","metrics":{"HOTA":"72.77 ","MOTA":"86.41"},"uses_additional_data":false,"paper_date":"2021-03-12","paper":"/paper/monocular-quasi-dense-3d-object-tracking","paper_url":"https://arxiv.org/abs/2103.07351v1","paper_title":"Monocular Quasi-Dense 3D Object Tracking","code":"https://github.com/SysCV/qd-3dt","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"AB3DMOT","metrics":{"HOTA":"69.99 ","MOTA":"83.84"},"uses_additional_data":false,"paper_date":"2019-07-09","paper":"/paper/a-baseline-for-3d-multi-object-tracking","paper_url":"https://arxiv.org/abs/1907.03961v5","paper_title":"3D Multi-Object Tracking: A Baseline and New Evaluation Metrics","code":"https://github.com/xinshuoweng/AB3DMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"JRMOT","metrics":{"HOTA":"69.61 ","MOTA":"85.70"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/jrmot-a-real-time-3d-multi-object-tracker-and","paper_url":"https://arxiv.org/abs/2002.08397v4","paper_title":"JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset","code":"https://github.com/StanfordVL/JRMOT_ROS","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":13,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"mmMOT","metrics":{"HOTA":"62.05","MOTA":"84.77"},"uses_additional_data":false,"paper_date":"2019-09-09","paper":"/paper/robust-multi-modality-multi-object-tracking","paper_url":"https://arxiv.org/abs/1909.03850v1","paper_title":"Robust Multi-Modality Multi-Object Tracking","code":"https://github.com/ZwwWayne/mmMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"SRK ODESA","metrics":{"MOTA":"90.03"},"uses_additional_data":false,"paper_date":"2020-11-20","paper":"/paper/learning-local-feature-descriptors-for","paper_url":"https://openaccess.thecvf.com/content/ACCV2020/html/Mykheievskyi_Learning_Local_Feature_Descriptors_for_Multiple_Object_Tracking_ACCV_2020_paper.html","paper_title":"Learning Local Feature Descriptors for Multiple Object Tracking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"MOSTFusion","metrics":{"MOTA":"84.83"},"uses_additional_data":false,"paper_date":"2019-02-10","paper":"/paper/mots-multi-object-tracking-and-segmentation","paper_url":"http://arxiv.org/abs/1902.03604v2","paper_title":"MOTS: Multi-Object Tracking and Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"mmMOT-normal","metrics":{"MOTA":"84.77"},"uses_additional_data":false,"paper_date":"2019-09-09","paper":"/paper/robust-multi-modality-multi-object-tracking","paper_url":"https://arxiv.org/abs/1909.03850v1","paper_title":"Robust Multi-Modality Multi-Object Tracking","code":"https://github.com/ZwwWayne/mmMOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"3DT","metrics":{"MOTA":"84.52"},"uses_additional_data":false,"paper_date":"2018-11-26","paper":"/paper/joint-monocular-3d-vehicle-detection-and","paper_url":"https://arxiv.org/abs/1811.10742v3","paper_title":"Joint Monocular 3D Vehicle Detection and Tracking","code":"https://github.com/ucbdrive/3d-vehicle-tracking","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"Mono3DT","metrics":{"MOTA":"84.52"},"uses_additional_data":false,"paper_date":"2018-11-26","paper":"/paper/joint-monocular-3d-vehicle-detection-and","paper_url":"https://arxiv.org/abs/1811.10742v3","paper_title":"Joint Monocular 3D Vehicle Detection and Tracking","code":"https://github.com/ucbdrive/3d-vehicle-tracking","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"RRC-IIITH","metrics":{"MOTA":"84.24"},"uses_additional_data":false,"paper_date":"2018-02-26","paper":"/paper/beyond-pixels-leveraging-geometry-and-shape","paper_url":"http://arxiv.org/abs/1802.09298v2","paper_title":"Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking","code":"https://github.com/JunaidCS032/MOTBeyondPixels","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"PMBM","metrics":{"MOTA":"80.39"},"uses_additional_data":false,"paper_date":"2018-02-27","paper":"/paper/mono-camera-3d-multi-object-tracking-using","paper_url":"http://arxiv.org/abs/1802.09975v1","paper_title":"Mono-Camera 3D Multi-Object Tracking Using Deep Learning Detections and PMBM Filtering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"MCMOT-CPD","metrics":{"MOTA":"78.90"},"uses_additional_data":false,"paper_date":"2016-08-30","paper":"/paper/multi-class-multi-object-tracking-using","paper_url":"http://arxiv.org/abs/1608.08434v1","paper_title":"Multi-Class Multi-Object Tracking using Changing Point Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"NOMT","metrics":{"MOTA":"78.15"},"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":29,"model":"MDP","metrics":{"MOTA":"76.59"},"uses_additional_data":false,"paper_date":"2015-12-01","paper":"/paper/learning-to-track-online-multi-object","paper_url":"http://openaccess.thecvf.com/content_iccv_2015/html/Xiang_Learning_to_Track_ICCV_2015_paper.html","paper_title":"Learning to Track: Online Multi-Object Tracking by Decision Making","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"DSM","metrics":{"MOTA":"76.15"},"uses_additional_data":false,"paper_date":"2018-06-29","paper":"/paper/end-to-end-learning-of-multi-sensor-3d","paper_url":"http://arxiv.org/abs/1806.11534v1","paper_title":"End-to-end Learning of Multi-sensor 3D Tracking by Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"SCEA","metrics":{"MOTA":"75.58"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/online-multi-object-tracking-via-structural","paper_url":"http://openaccess.thecvf.com/content_cvpr_2016/html/Yoon_Online_Multi-Object_Tracking_CVPR_2016_paper.html","paper_title":"Online Multi-Object Tracking via Structural Constraint Event Aggregation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"CIWT","metrics":{"MOTA":"75.39"},"uses_additional_data":false,"paper_date":"2018-09-19","paper":"/paper/combined-image-and-world-space-tracking-in","paper_url":"http://arxiv.org/abs/1809.07357v1","paper_title":"Combined Image- and World-Space Tracking in Traffic Scenes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"NOMT-HM","metrics":{"MOTA":"75.20"},"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":34,"model":"mbodSSP","metrics":{"MOTA":"72.69"},"uses_additional_data":false,"paper_date":"2014-07-23","paper":"/paper/followme-efficient-online-min-cost-flow","paper_url":"http://arxiv.org/abs/1407.6251v2","paper_title":"FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation","code":null,"n_code_links":0,"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":7,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":26,"n_unverified":53,"n_samples":79,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":27,"n_unverified":55,"n_samples":82,"n_pointer_only_licence":2,"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"}}}