{"url":"/method/fairmot","slug":"fairmot","name":"FairMOT","full_name":"FairMOT","full_name_withheld":false,"description_markdown":"**FairMOT** is a model for multi-object tracking which consists of two homogeneous branches to predict pixel-wise objectness scores and re-ID features. The achieved fairness between the tasks is used to achieve high levels of detection and tracking accuracy. The detection branch is implemented in an anchor-free style which estimates object centers and sizes represented as position-aware measurement maps. Similarly, the re-ID branch estimates a re-ID feature for each pixel to characterize the object centered at the pixel. Note that the two branches are completely homogeneous which essentially differs from the previous methods which perform detection and re-ID in a cascaded style. It is also worth noting that FairMOT operates on high-resolution feature maps of strides four while the previous anchor-based methods operate on feature maps of stride 32. The elimination of anchors as well as the use of high-resolution feature maps better aligns re-ID features to object centers which significantly improves the tracking accuracy.","description_state":"present","introduced_year":null,"introduced_by":{"title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","paper":"/paper/a-simple-baseline-for-multi-object-tracking","first_author":"Yifu Zhang","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/a-simple-baseline-for-multi-object-tracking"},"source":{"url":"https://arxiv.org/abs/2004.01888v6","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Multi-Object Tracking Models","url":"/methods/category/multi-object-tracking-models","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":7,"papers_newest_first":[{"paper":"/paper/leveraging-foundation-models-via-knowledge","title":"Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT","date":"2024-07-25","arxiv_id":"2407.18288","n_code_links":1,"syntology":null},{"paper":null,"title":"AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes","date":"2023-08-15","arxiv_id":"2308.07537","n_code_links":0,"syntology":null},{"paper":null,"title":"Shadow-Background-Noise 3D Spatial Decomposition Using Sparse Low-Rank Gaussian Properties for Video-SAR Moving Target Shadow Enhancement","date":"2022-07-07","arxiv_id":"2207.03064","n_code_links":0,"syntology":null},{"paper":"/paper/improving-object-detection-multi-object","title":"Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones","date":"2022-01-05","arxiv_id":"2201.01494","n_code_links":4,"syntology":null},{"paper":"/paper/trasw-tracklet-switch-adversarial-attacks","title":"Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers","date":"2021-11-17","arxiv_id":"2111.08954","n_code_links":5,"syntology":null},{"paper":"/paper/joint-learning-architecture-for-multiple","title":"Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting","date":"2021-08-24","arxiv_id":"2108.10543","n_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","arxiv_id":"2004.01888","n_code_links":33,"syntology":{"ran":8,"of":53,"unverified":45,"pointer_only":0}}],"papers_shown":7,"tasks":[{"task":"/task/object-tracking","name":"Object Tracking","papers":6},{"task":"/task/multi-object-tracking","name":"Multi-Object Tracking","papers":5},{"task":"/task/multiple-object-tracking","name":"Multiple Object Tracking","papers":4},{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/disaster-response","name":"Disaster Response","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/shadow-detection","name":"Shadow Detection","papers":1},{"task":"/task/trajectory-forecasting","name":"Trajectory Forecasting","papers":1},{"task":"/task/motion-prediction","name":"motion prediction","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":16,"n_tasks":16,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2023","papers":1},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/fairmot"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}