{"url":"/dataset/mot17","name":"MOT17","full_name":"Multiple Object Tracking 17","description_markdown":"The **Multiple Object Tracking 17** (**MOT17**) dataset is a dataset for multiple object tracking. Similar to its previous version MOT16, this challenge contains seven different indoor and outdoor scenes of public places with pedestrians as the objects of interest. A video for each scene is divided into two clips, one for training and the other for testing. The dataset provides detections of objects in the video frames with three detectors, namely SDP, Faster-RCNN and DPM. The challenge accepts both on-line and off-line tracking approaches, where the latter are allowed to use the future video frames to predict tracks.\r\n\r\nSource: [Deep Affinity Network for Multiple Object Tracking](https://arxiv.org/abs/1810.11780)\r\nImage Source: [https://www.researchgate.net/figure/Visualization-of-selected-sequences-from-the-MOT17-benchmark-dataset_fig4_337133502](https://www.researchgate.net/figure/Visualization-of-selected-sequences-from-the-MOT17-benchmark-dataset_fig4_337133502)","description_withheld":null,"homepage":"https://motchallenge.net/data/MOT17/","introduced_date":"2016-03-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/mot16-a-benchmark-for-multi-object-tracking","title":"MOT16: A Benchmark for Multi-Object Tracking","first_author":"Anton Milan","url":null},"license":{"name":"CC BY-NC-SA 3.0","url":"https://motchallenge.net/"},"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":"Online Multi-Object Tracking","url":"/task/online-multi-object-tracking","datasets_with_task":"/datasets/task/online-multi-object-tracking"}],"languages":[],"variants":["MOT17"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmtracking","url":"https://github.com/open-mmlab/mmtracking/blob/master/docs/dataset.md","frameworks":["pytorch"]}],"num_papers_in_archive":291,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset_variant":"MOT17","rows":48,"metrics":["HOTA","MOTA","IDF1","AssA","DetA","e2e-MOT","Speed (FPS)"],"first_row_in_archive_order":{"model":"TrackTrack","paper":"/paper/focusing-on-tracks-for-online-multi-object","metrics":{"AssA":"68.2","HOTA":"67.1","IDF1":"83.1","MOTA":"81.8"},"code_links":[{"title":"kamkyu94/TrackTrack","url":"https://github.com/kamkyu94/TrackTrack"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/online-multi-object-tracking-on-mot17","task":"Online Multi-Object Tracking","dataset_variant":"MOT17","rows":2,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"Tracktor++","paper":"/paper/tracking-without-bells-and-whistles","metrics":{"MOTA":"53.5"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/focusing-on-tracks-for-online-multi-object","title":"Focusing on Tracks for Online Multi-Object Tracking","date":"2025-06-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptrack-adaptive-thresholding-based","title":"AdapTrack: Adaptive Thresholding-Based Matching For Multi-object Tracking","date":"2024-09-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-confidence-aware-matching-strategy-for","title":"A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking","date":"2024-09-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/interacting-multiple-model-based-joint","title":"One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation","date":"2024-09-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boosttrack-using-tracklet-information-to","title":"BoostTrack++: using tracklet information to detect more objects in multiple object tracking","date":"2024-08-23","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/featuresort-essential-features-for-effective","title":"FeatureSORT: Essential Features for Effective Tracking","date":"2024-07-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/boosttrack-boosting-the-similarity-measure","title":"BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking","date":"2024-04-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sfsort-scene-features-based-simple-online","title":"SFSORT: Scene Features-based Simple Online Real-Time Tracker","date":"2024-04-11","rows_on_this_dataset":1,"code_links":1,"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":1,"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/learning-data-association-for-multi-object","title":"Learning Data Association for Multi-Object Tracking using Only Coordinates","date":"2024-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ucmctrack-multi-object-tracking-with-uniform","title":"UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation","date":"2023-12-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contrastive-learning-for-multi-object","title":"Contrastive Learning for Multi-Object Tracking with Transformers","date":"2023-11-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sparsetrack-multi-object-tracking-by","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","date":"2023-06-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/bridging-the-gap-between-end-to-end-and-non","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","date":"2023-05-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deep-oc-sort-multi-pedestrian-tracking-by","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","date":"2023-02-23","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/smiletrack-similarity-learning-for-multiple","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","date":"2022-11-16","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/multiple-object-tracking-from-appearance-by","title":"Multiple Object Tracking from appearance by hierarchically clustering tracklets","date":"2022-10-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lmot-efficient-light-weight-detection-and","title":"LMOT: Efficient Light-Weight Detection and Tracking in Crowds","date":"2022-08-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transformer-based-assignment-decision-network","title":"Transformer-based assignment decision network for multiple object tracking","date":"2022-08-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/towards-grand-unification-of-object-tracking","title":"Towards Grand Unification of Object Tracking","date":"2022-07-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bot-sort-robust-associations-multi-pedestrian","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","date":"2022-06-29","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":4,"samples_unverified":6,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/detection-recovery-in-online-multi-object","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","date":"2022-05-02","rows_on_this_dataset":1,"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":1,"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/simpletrack-rethinking-and-improving-the-jde","title":"SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking","date":"2022-03-08","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/strongsort-make-deepsort-great-again","title":"StrongSORT: Make DeepSORT Great Again","date":"2022-02-28","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":3,"samples_unverified":17,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/online-multi-object-tracking-with","title":"Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation","date":"2022-01-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/multiple-object-tracking-with-mixture-density","title":"Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation","date":"2021-06-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/motr-end-to-end-multiple-object-tracking-with","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","date":"2021-05-07","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/spatial-temporal-graph-transformer-for","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","date":"2021-04-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/2103-15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","date":"2021-03-28","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/track-to-detect-and-segment-an-online-multi","title":"Track to Detect and Segment: An Online Multi-Object Tracker","date":"2021-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deft-detection-embeddings-for-tracking","title":"DEFT: Detection Embeddings for Tracking","date":"2021-02-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/trackformer-multi-object-tracking-with","title":"TrackFormer: Multi-Object Tracking with Transformers","date":"2021-01-07","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/lifted-disjoint-paths-with-application-in-1","title":"Lifted Disjoint Paths with Application in Multiple Object Tracking","date":"2020-06-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-detection-and-multi-object-tracking","title":"Joint Object Detection and Multi-Object Tracking with Graph Neural Networks","date":"2020-06-23","rows_on_this_dataset":1,"code_links":1,"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":1,"code_links":3,"syntology":null},{"paper":"/paper/learning-a-neural-solver-for-multiple-object-1","title":"Learning a Neural Solver for Multiple Object Tracking","date":"2020-06-01","rows_on_this_dataset":1,"code_links":1,"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":1,"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/online-multi-object-tracking-framework-with","title":"Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management","date":"2019-07-31","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deepmot-a-differentiable-framework-for","title":"How To Train Your Deep Multi-Object Tracker","date":"2019-06-15","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/multiple-people-tracking-using-body-and-joint","title":"Multiple People Tracking using Body and Joint Detections","date":"2019-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tracking-without-bells-and-whistles","title":"Tracking without bells and whistles","date":"2019-03-13","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":3,"samples_unverified":11,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploit-the-connectivity-multi-object","title":"Exploit the Connectivity: Multi-Object Tracking with TrackletNet","date":"2018-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fusion-of-head-and-full-body-detectors-for","title":"Fusion of Head and Full-Body Detectors for Multi-Object Tracking","date":"2017-05-23","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":12,"samples_harvested":181,"samples_ran":60,"samples_unverified":121,"pointer_only_for_licence":13,"papers_with_no_sample_that_ran":1,"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."}