Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.12.2025 · 21 (12) · 1-21
DOI: 10.1145/3749105 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 21.11.2025. Verfasst von Chongwei Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Taishan Scholar Program of Shandong Province.
Abstract (Originalsprache)
Recent advances in multi-object tracking (MOT) have demonstrated significant success in short-term association within the separated tracking-by-detection online paradigm. However, long-term tracking remains challenging. While graph-based approaches address this by modeling trajectories as global graphs, these methods are unsuitable for real-time applications due to their non-online nature. In this article, we review the concept of trajectory graphs and propose a novel perspective by representing them as directed acyclic graphs. This representation can be described using frame-ordered object sequences and binary adjacency matrices. We observe that this structure naturally aligns with Transformer attention mechanisms, enabling us to model the association problem using a classic Transformer architecture. Based on this insight, we introduce a concise pure transformer (PuTR) to validate the effectiveness of Transformer in unifying short- and long-term tracking for separated online MOT. Extensive experiments on four diverse datasets (SportsMOT, DanceTrack, MOT17, and MOT20) demonstrate that PuTR effectively establishes a solid baseline compared to existing foundational online methods while exhibiting superior domain adaptation capabilities. Furthermore, the separated nature enables efficient training and inference, making it suitable for practical applications. Implementation code and trained models are available at https://github.com/chongweiliu/PuTR .
Förderung
- National Natural Science Foundation of China
- Taishan Scholar Program of Shandong Province
Zitieren
APA
Liu, C., Li, H., Wang, Z., & Xu, R. (2025). Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(12), 1-21. https://doi.org/10.1145/3749105
Vancouver
Liu C, Li H, Wang Z, Xu R. Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(12):1-21. doi:10.1145/3749105
BibTeX
@article{Liu2025,
author = {Liu, Chongwei and Li, Haojie and Wang, Zhihui and Xu, Rui},
title = {Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {12},
pages = {1--21},
doi = {10.1145/3749105}
}
EUVIMED