CasCenter: A Cascaded Center Network for Visual Tracking
IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 2864-2875
DOI: 10.1109/tce.2025.3547962 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Qun Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben.
Abstract (Originalsprache)
Object tracking has advanced significantly with Transformer-based architectures in recent years. However, replacing convolutional layers with global cross-attention in the tracking head of these architectures results in a loss of object-centric inductive bias. Consequently, existing Transformer-based methods often struggle with complex real-life scenarios, such as low resolution, background clutter, and scale variation. To address this issue, we propose a new Vision Transformer-based anchor-free tracking framework named CasCenter. Specifically, the framework features a cascade attention module in the decoder that propagates tracking cues from the previous tracking head to refine object features in a coarse-to-fine manner, enabling the tracker to focus more effectively on the target. Additionally, to further improve tracking stability and accuracy, we incorporate SIoU loss, a multi-scale tracking head, and a Gaussian mask-constrained cross-attention mechanism that emphasizes target regions while suppressing background interference. Extensive experiments demonstrate the superiority of our proposed CasCenter.
Zitieren
APA
Li, Q., Zhang, H., Yang, K., Shi, Y., Zeng, D., & Yap, W. (2025). CasCenter: A Cascaded Center Network for Visual Tracking. IEEE Transactions on Consumer Electronics, 71(2), 2864-2875. https://doi.org/10.1109/tce.2025.3547962
Vancouver
Li Q, Zhang H, Yang K, Shi Y, Zeng D, Yap W. CasCenter: A Cascaded Center Network for Visual Tracking. IEEE Transactions on Consumer Electronics. 2025;71(2):2864-2875. doi:10.1109/tce.2025.3547962
BibTeX
@article{Li2025,
author = {Li, Qun and Zhang, Haijun and Yang, Kai and Shi, Yong-Guo and Zeng, Deqiang and Yap, Wun-She},
title = {CasCenter: A Cascaded Center Network for Visual Tracking},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {2},
pages = {2864--2875},
doi = {10.1109/tce.2025.3547962}
}
EUVIMED