P2FTrack: Multi-Object Tracking with Motion Prior and Feature Posterior
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.01.2025 · 21 (1) · 1-22
DOI: 10.1145/3700443 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 23.12.2024. Verfasst von Hong Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Multiple object tracking (MOT) has emerged as a crucial component of the rapidly developing computer vision. However, existing multi-object tracking methods often overlook the relationship between features and motion, hindering the ability to strike a performance balance between coupled motion and complex scenes. In this work, we propose a novel end-to-end multi-object tracking method that integrates motion and feature information. To achieve this, we introduce a motion prior generator that transforms motion information into attention masks. Additionally, we leverage prior-posterior fusion multi-head attention to combine the motion-derived priors and attention-based posteriors. Our proposed method is extensively evaluated on MOT17 and DanceTrack datasets through comprehensive experiments and ablation studies, demonstrating state-of-the-art performance in the feature-based method with reasonable speed.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, H., Wan, J., Zhang, J., Yuan, D., Li, X., & Yang, Y. (2025). P2FTrack: Multi-Object Tracking with Motion Prior and Feature Posterior. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(1), 1-22. https://doi.org/10.1145/3700443
Vancouver
Zhang H, Wan J, Zhang J, Yuan D, Li X, Yang Y. P2FTrack: Multi-Object Tracking with Motion Prior and Feature Posterior. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(1):1-22. doi:10.1145/3700443
BibTeX
@article{Zhang2025,
author = {Zhang, Hong and Wan, Jiaxu and Zhang, Jing and Yuan, Ding and Li, Xuliang and Yang, Yifan},
title = {P2FTrack: Multi-Object Tracking with Motion Prior and Feature Posterior},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {1},
pages = {1--22},
doi = {10.1145/3700443}
}
EUVIMED