EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Siamese Attention Networks with Adaptive Templates for Visual Tracking

Bo Zhang, Zhixue Liang, Wenyong Dong

Mobile Information Systems · 19.09.2022 · 2022 · 1-10

DOI: 10.1155/2022/7056149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mobile Information Systems, erschienen am 19.09.2022. Verfasst von Bo Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual object tracking takes an important role in realistic applications, such as video understanding, unmanned auto vehicles, and autonomous robots. Although the Siamese-based tracker has achieved good performance in tracking tasks, the existing methods using initial template or updating template with simple strategy result in the performance degradation of the model when the target varies in realistic scenarios such as target occlusion, scale variation, and deformation. In this paper, we propose a visual tracking framework with adaptive template update and spatiotemporal attention, named SiamAttnAT. Specially, we propose a historical template selecting strategy and a template adaptively generating method for robust tracking. In addition, we apply the proposed mechanisms to the employed baseline SiamRPN++. Extensive experiments and comparisons with state-of-the-art trackers on short-term and long-term visual tracking benchmarks including VOT2018, OTB-100, UAV123, NFS, and LaSOT show that the proposed framework achieves the outstanding performance with a considerable real-time speed, verifying its efficiency and effectiveness.

Zitieren

APA

Zhang, B., Liang, Z., & Dong, W. (2022). Siamese Attention Networks with Adaptive Templates for Visual Tracking. Mobile Information Systems, 2022, 1-10. https://doi.org/10.1155/2022/7056149

Vancouver

Zhang B, Liang Z, Dong W. Siamese Attention Networks with Adaptive Templates for Visual Tracking. Mobile Information Systems. 2022;2022:1-10. doi:10.1155/2022/7056149

BibTeX
@article{Zhang2022,
  author = {Zhang, Bo and Liang, Zhixue and Dong, Wenyong},
  title = {Siamese Attention Networks with Adaptive Templates for Visual Tracking},
  journal = {Mobile Information Systems},
  year = {2022},
  volume = {2022},
  pages = {1--10},
  doi = {10.1155/2022/7056149}
}
Kostenlos starten →