{"url":"/sota/multi-object-tracking-on-dancetrack","task":{"name":"Multi-Object Tracking","url":"/task/multi-object-tracking","note":null},"dataset":{"name":"DanceTrack","url":"/dataset/dancetrack"},"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","MOTA","IDF1","AssA","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,"MOTA":null,"IDF1":null,"AssA":null,"DetA":null}},"counts":{"rows":37,"rows_with_code":33,"rows_with_paper_page":37,"rows_dated":37,"rows_using_additional_data":11},"rows":[{"rank_in_archive_order":1,"model":"SAM2MOT","metrics":{"AssA":"72.3","DetA":"79.9","HOTA":"75.9","IDF1":"84.4","MOTA":"88.9"},"uses_additional_data":false,"paper_date":"2025-04-06","paper":"/paper/sam2mot-a-novel-paradigm-of-multi-object","paper_url":"https://arxiv.org/abs/2504.04519v3","paper_title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","code":"https://github.com/TripleJoy/SAM2MOT","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MOTIP (Deformable DETR, with DanceTrack val and CrowdHuman)","metrics":{"AssA":"65.9","DetA":"82.6","HOTA":"73.7","IDF1":"78.4","MOTA":"92.7"},"uses_additional_data":true,"paper_date":"2024-03-25","paper":"/paper/multiple-object-tracking-as-id-prediction","paper_url":"https://arxiv.org/abs/2403.16848v1","paper_title":"Multiple Object Tracking as ID Prediction","code":"https://github.com/MCG-NJU/MOTIP","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MOTRv2","metrics":{"AssA":"64.4","DetA":"83.7","HOTA":"73.4","IDF1":"76.0","MOTA":"92.1"},"uses_additional_data":true,"paper_date":"2022-11-17","paper":"/paper/motrv2-bootstrapping-end-to-end-multi-object","paper_url":"https://arxiv.org/abs/2211.09791v2","paper_title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","code":"https://github.com/megvii-research/MOTRv2","n_code_links":4,"syntology":null},{"rank_in_archive_order":4,"model":"MOTIP (Deformable DETR, with CrowdHuman)","metrics":{"AssA":"62.8","DetA":"81.3","HOTA":"71.4","IDF1":"76.3","MOTA":"91.6"},"uses_additional_data":true,"paper_date":"2024-03-25","paper":"/paper/multiple-object-tracking-as-id-prediction","paper_url":"https://arxiv.org/abs/2403.16848v1","paper_title":"Multiple Object Tracking as ID Prediction","code":"https://github.com/MCG-NJU/MOTIP","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MOTIP (DAB-Deformable DETR)","metrics":{"AssA":"60.8","DetA":"80.8","HOTA":"70.0","IDF1":"75.1","MOTA":"91.0"},"uses_additional_data":false,"paper_date":"2024-03-25","paper":"/paper/multiple-object-tracking-as-id-prediction","paper_url":"https://arxiv.org/abs/2403.16848v1","paper_title":"Multiple Object Tracking as ID Prediction","code":"https://github.com/MCG-NJU/MOTIP","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CO-MOT","metrics":{"AssA":"58.9","DetA":"82.1","HOTA":"69.4","IDF1":"71.9","MOTA":"91.2"},"uses_additional_data":true,"paper_date":"2023-05-22","paper":"/paper/bridging-the-gap-between-end-to-end-and-non","paper_url":"https://arxiv.org/abs/2305.12724v1","paper_title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","code":"https://github.com/bingfengyan/visam","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"CAMELTrack (fully online)","metrics":{"HOTA":"69.3"},"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":8,"model":"MeMOTR","metrics":{"AssA":"58.4","DetA":"80.5","HOTA":"68.5","IDF1":"71.2","MOTA":"89.9"},"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":9,"model":"MOTIP (Deformable DETR)","metrics":{"AssA":"57.6","DetA":"79.4","HOTA":"67.5","IDF1":"72.2","MOTA":"90.3"},"uses_additional_data":false,"paper_date":"2024-03-25","paper":"/paper/multiple-object-tracking-as-id-prediction","paper_url":"https://arxiv.org/abs/2403.16848v1","paper_title":"Multiple Object Tracking as ID Prediction","code":"https://github.com/MCG-NJU/MOTIP","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"MT_IOT","metrics":{"AssA":"52.95","DetA":"84.14","HOTA":"66.66","IDF1":"70.6","MOTA":"93.97"},"uses_additional_data":true,"paper_date":"2022-12-07","paper":"/paper/multiple-object-tracking-challenge-technical","paper_url":"https://arxiv.org/abs/2212.03586v1","paper_title":"Multiple Object Tracking Challenge Technical Report for Team MT_IoT","code":"https://github.com/BingfengYan/DS_OCSORT","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"AED","metrics":{"AssA":"54.3","DetA":"82.0","HOTA":"66.6","IDF1":"69.7","MOTA":"92.2"},"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":12,"model":"TrackTrack","metrics":{"AssA":"52.9","HOTA":"66.5","IDF1":"67.8","MOTA":"93.6"},"uses_additional_data":true,"paper_date":"2025-06-15","paper":"/paper/focusing-on-tracks-for-online-multi-object","paper_url":"https://cvpr.thecvf.com/virtual/2025/poster/35174","paper_title":"Focusing on Tracks for Online Multi-Object Tracking","code":"https://github.com/kamkyu94/TrackTrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"IMM-JHSE","metrics":{"AssA":"55.41","HOTA":"66.24","IDF1":"71.72","MOTA":"89.95"},"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":14,"model":"Hybrid-SORT-ReID","metrics":{"AssA":"52.6","DetA":"82.2","HOTA":"65.7","IDF1":"67.4","MOTA":"91.8"},"uses_additional_data":false,"paper_date":"2023-08-01","paper":"/paper/hybrid-sort-weak-cues-matter-for-online-multi","paper_url":"https://arxiv.org/abs/2308.00783v2","paper_title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"UCMCTrack","metrics":{"HOTA":"63.6","IDF1":"65.0"},"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":16,"model":"MeMOTR (Deformable DETR)","metrics":{"AssA":"52.3","DetA":"77.0","HOTA":"63.4","IDF1":"65.5","MOTA":"85.4"},"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":"DeepMoveSORT","metrics":{"AssA":"48.6","DetA":"82.0","HOTA":"63.0","IDF1":"65.0","MOTA":"92.6"},"uses_additional_data":false,"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":18,"model":"Hybrid-SORT","metrics":{"AssA":"47.4","DetA":"81.9","HOTA":"62.2","IDF1":"63.0","MOTA":"91.6"},"uses_additional_data":false,"paper_date":"2023-08-01","paper":"/paper/hybrid-sort-weak-cues-matter-for-online-multi","paper_url":"https://arxiv.org/abs/2308.00783v2","paper_title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"C-TWiX","metrics":{"AssA":"47.2","DetA":"81.8","HOTA":"62.1","IDF1":"63.6","MOTA":"91.4"},"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":20,"model":"CMTrack","metrics":{"AssA":"46.4","HOTA":"61.8","IDF1":"63.3","MOTA":"92.5"},"uses_additional_data":true,"paper_date":"2024-09-27","paper":"/paper/a-confidence-aware-matching-strategy-for","paper_url":"https://ieeexplore.ieee.org/document/10647729","paper_title":"A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking","code":"https://github.com/kamkyu94/CMTrack","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"Deep OC-SORT","metrics":{"AssA":"45.8","DetA":"82.2","HOTA":"61.3","IDF1":"61.5","MOTA":"92.3"},"uses_additional_data":false,"paper_date":"2023-02-23","paper":"/paper/deep-oc-sort-multi-pedestrian-tracking-by","paper_url":"https://arxiv.org/abs/2302.11813v1","paper_title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","code":"https://github.com/mikel-brostrom/boxmot","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":8,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"C-BIoU","metrics":{"AssA":"45.4","DetA":"81.3","HOTA":"60.6","IDF1":"61.6","MOTA":"91.6"},"uses_additional_data":false,"paper_date":"2022-11-24","paper":"/paper/hard-to-track-objects-with-irregular-motions","paper_url":"https://arxiv.org/abs/2211.14317v3","paper_title":"Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space","code":"https://github.com/Guepardow/TWiX","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"MotionTrack","metrics":{"AssA":"41.7","DetA":"81.4","HOTA":"58.2","IDF1":"58.6","MOTA":"91.3"},"uses_additional_data":true,"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":24,"model":"ETTrack","metrics":{"AssA":"39.1","DetA":"81.7","HOTA":"56.4","IDF1":"57.5","MOTA":"92.2"},"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":25,"model":"MoveSORT","metrics":{"AssA":"38.7","DetA":"81.6","HOTA":"56.1","IDF1":"56.0","MOTA":"91.8"},"uses_additional_data":false,"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":26,"model":"MambaMOT","metrics":{"AssA":"39.0","DetA":"80.8","HOTA":"56.1","IDF1":"54.9","MOTA":"90.3"},"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":27,"model":"Fast-StrongSORT","metrics":{"AssA":"38.8","HOTA":"55.9","IDF1":"54.6"},"uses_additional_data":false,"paper_date":"2024-09-10","paper":"/paper/when-to-extract-reid-features-a-selective","paper_url":"https://arxiv.org/abs/2409.06617v2","paper_title":"When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking","code":"https://github.com/emirhanbayar/fast-strongsort","n_code_links":2,"syntology":null},{"rank_in_archive_order":28,"model":"SparseTrack","metrics":{"AssA":"39.3","DetA":"79.2","HOTA":"55.7","IDF1":"58.1","MOTA":"91.3"},"uses_additional_data":false,"paper_date":"2023-06-08","paper":"/paper/sparsetrack-multi-object-tracking-by","paper_url":"https://arxiv.org/abs/2306.05238v2","paper_title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","code":"https://github.com/hustvl/sparsetrack","n_code_links":2,"syntology":null},{"rank_in_archive_order":29,"model":"OC-SORT","metrics":{"AssA":"38.0","HOTA":"55.1","IDF1":"54.2","MOTA":"89.4"},"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":30,"model":"MOTR","metrics":{"AssA":"40.2","DetA":"73.5","HOTA":"54.2","IDF1":"51.5","MOTA":"79.7"},"uses_additional_data":false,"paper_date":"2021-05-07","paper":"/paper/motr-end-to-end-multiple-object-tracking-with","paper_url":"https://arxiv.org/abs/2105.03247v4","paper_title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","code":"https://github.com/megvii-model/MOTR","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"FCG","metrics":{"AssA":"29.9","DetA":"79.8","HOTA":"48.7","IDF1":"46.5","MOTA":"89.9"},"uses_additional_data":true,"paper_date":"2022-10-07","paper":"/paper/multiple-object-tracking-from-appearance-by","paper_url":"https://arxiv.org/abs/2210.03355v1","paper_title":"Multiple Object Tracking from appearance by hierarchically clustering tracklets","code":"https://github.com/nii-satoh-lab/mot_fcg","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"ByteTrack","metrics":{"AssA":"31.5","DetA":"70.5","HOTA":"47.1","IDF1":"51.9","MOTA":"88.2"},"uses_additional_data":false,"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":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"QDTrack","metrics":{"AssA":"29.2","DetA":"72.1","HOTA":"45.7","IDF1":"44.8","MOTA":"83.0"},"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":34,"model":"TransTrack","metrics":{"AssA":"27.5","DetA":"72.1","HOTA":"45.7","IDF1":"44.8","MOTA":"83.0"},"uses_additional_data":false,"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":35,"model":"TraDes","metrics":{"AssA":"25.4","DetA":"74.5","HOTA":"43.3","IDF1":"41.2","MOTA":"86.2"},"uses_additional_data":false,"paper_date":"2021-03-16","paper":"/paper/track-to-detect-and-segment-an-online-multi","paper_url":"https://arxiv.org/abs/2103.08808v1","paper_title":"Track to Detect and Segment: An Online Multi-Object Tracker","code":"https://github.com/JialianW/TraDeS","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"CenterTrack","metrics":{"AssA":"22.6","DetA":"78.1","HOTA":"41.8","IDF1":"35.7","MOTA":"86.8"},"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":37,"model":"FairMOT","metrics":{"AssA":"23.8","DetA":"66.7","HOTA":"39.7","IDF1":"40.8","MOTA":"82.2"},"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":8,"n_unverified":45,"n_samples":53,"n_pointer_only_licence":0}}],"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":12,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":54,"n_unverified":96,"n_samples":150,"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":94,"n_unverified":100,"n_samples":194,"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"}}}