Siamese Visual Tracking With Multi-Parallel Interactive Transformers
IEEE Transactions on Circuits and Systems for Video Technology · 2025-10 · 35 (10) · 10353-10366
DOI: 10.1109/tcsvt.2025.3569633 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-10. Verfasst von Wuwei Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Shaanxi Province, Shaanxi Youth Talent Lifting Plan of Shaanxi Association for Science and Technology.
Abstract (Originalsprache)
In recent years, Siamese network-based visual tracking methods have gained popularity and success in terms of efficiency and accuracy. However, typical Siamese trackers utilize two independent weight-sharing streams to describe the exemplar and search region without any interaction between the two streams. As a result, such trackers employ only shallow cross-correlation or correlation filters to obtain the final information association, which neglects the deep interaction between the exemplar and search region and may reduce the discriminative power of the trackers. To address this issue, we propose a novel multi-parallel interactive transformer-based (MPIT) tracking framework to introduce sufficient interaction so that the two streams can guide the prediction heads to focus on the target more easily. Unlike recent one-stream transformer-based trackers that directly concatenate template and search tokens to perform joint feature learning, our multi-parallel interactive framework introduces a transmission band module to deliver global information for both the exemplar and the search region with low computational cost. Moreover, to integrate dynamic information, we incorporate temporal level extraction into the tracking framework to increase the variety of the templates. The experimental results show that the proposed MPIT method achieves a remarkable tracking speed of 136 frames per second (FPS) while attaining performance better than or comparable to that of state-of-the-art trackers.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Shaanxi Province
- Shaanxi Youth Talent Lifting Plan of Shaanxi Association for Science and Technology
Zitieren
APA
Wang, W., Lv, M., Zhu, L., Han, T., Zhang, Y., & Li, Y. (2025). Siamese Visual Tracking With Multi-Parallel Interactive Transformers. IEEE Transactions on Circuits and Systems for Video Technology, 35(10), 10353-10366. https://doi.org/10.1109/tcsvt.2025.3569633
Vancouver
Wang W, Lv M, Zhu L, Han T, Zhang Y, Li Y. Siamese Visual Tracking With Multi-Parallel Interactive Transformers. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(10):10353-10366. doi:10.1109/tcsvt.2025.3569633
BibTeX
@article{Wang2025,
author = {Wang, Wuwei and Lv, Meibo and Zhu, Lin and Han, Tuo and Zhang, Yi and Li, Yuanqing},
title = {Siamese Visual Tracking With Multi-Parallel Interactive Transformers},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {10},
pages = {10353--10366},
doi = {10.1109/tcsvt.2025.3569633}
}
EUVIMED