Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 89 of the 89 references it cites were found in a registry or an index.

FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking

Open access
Zhang, Yifu, Wang, Chunyu, Wang, Xinggang, Zeng, Wenjun, Liu, Wenyu·2021·International Journal of Computer Vision

Abstract

Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency. However, we find that the two tasks tend to compete with each other which need to be carefully addressed. In particular, previous works usually treat re-ID as a secondary task whose accuracy is heavily affected by the primary detection task. As a result, the network is biased to the primary detection task which is not fair to the re-ID task. To solve the problem, we present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. Note that it is not a naive combination of CenterNet and re-ID. Instead, we present a bunch of detailed designs which are critical to achieve good tracking results by thorough empirical studies. The resulting approach achieves high accuracy for both detection and tracking. The approach outperforms the state-of-the-art methods by a large margin on several public datasets. The source code and pre-trained models are released at https://github.com/ifzhang/FairMOT.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s11263-021-01513-4

Cites

89 of 89 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 89 references

Research works printed but not linked: 14

  1. Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., & Leal-Taixé, L. (2020). Mot20: A benchmark for multi object tracking in crowded scenes. arXiv preprint arXiv:2003.09003. · arXiv
  2. Han, S., Huang, P., Wang, H., Yu, E., Liu, D., Pan, X., & Zhao, J. (2020) Mat: Motion-aware multi-object tracking. arXiv preprint arXiv:2009.04794 · arXiv
  3. Han, W., Khorrami, P., Paine, T. L., Ramachandran, P., Babaeizadeh, M., Shi, H., Li, J., Yan, S., & Huang, T. S. (2016). Seq-nms for video object detection. arXiv preprint arXiv:1602.08465. · arXiv
  4. Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737. · arXiv
  5. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. · arXiv
  6. Leal-Taixé, L., Milan, A., Reid, I., Roth, S., & Schindler, K. (2015). Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942. · arXiv
  7. Liang, C., Zhang, Z., Lu, Y., Zhou, X., Li, B., Ye, X., & Zou, J. (2020). Rethinking the competition between detection and reid in multi-object tracking. arXiv preprint arXiv:2010.12138. · arXiv
  8. Milan, A., Leal-Taixé, L., Reid, I., Roth, S., & Schindler, K. (2016) Mot16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831. · arXiv
  9. Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. · arXiv
  10. Shan, C., Wei, C., Deng, B., Huang, J., Hua, X. S., Cheng, X., & Liang, K. (2020). Fgagt: Flow-guided adaptive graph tracking. arXiv preprint arXiv:2010.09015. · arXiv
  11. Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., & Sun, J. (2018). Crowdhuman: A benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123. · arXiv
  12. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. · arXiv
  13. Sun, S., Akhtar, N., Song, H., Mian, A. S., & Shah, M. (2019). Deep affinity network for multiple object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 104–119.
  14. Valmadre, J., Bewley, A., Huang, J., Sun, C., Sminchisescu, C., & Schmid, C. (2021). Local metrics for multi-object tracking. arXiv preprint arXiv:2104.02631. · arXiv

Cited by

See all 1,861

Metadata

Authors
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W.
Affiliations
  • Huazhong University of Science and Technology (CN)
  • Microsoft Research Asia (China) (CN)
Corresponding author
Wang, Xinggang
Venue
International Journal of Computer Vision
Published
2021-09-03
Volume
129
Issue
11
Pages
3069-3087
ISSN
  • 0920-5691 (ISSN-L)
  • 1573-1405
OpenAlex
W3084173793
Cited by
1,861
References
89
Citations by year
2026: 296 · 2025: 427 · 2024: 402 · 2023: 345 · 2022: 281 · 2021: 100
FWCI
101.51
Type
journal article
Language
en
Open access
Licence
Locations
  • International Journal of Computer Vision (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
Keywords
multi-target tracking, person re-identification, object detection, CenterNet, anchor-free detection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking. https://app.cochat.ai/papers/10.1007/s11263-021-01513-4
The paper
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021). FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking. International Journal of Computer Vision. https://doi.org/10.1007/s11263-021-01513-4

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.