EUVIMEDEUVIMED entdecken
Crossref

AVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking

Yuanliang Xue, Bineng Zhong, Guodong Jin, Tao Shen, Lining Tan, Ning Li, Yaozong Zheng

IEEE Transactions on Circuits and Systems for Video Technology · 2025-08 · 35 (8) · 7554-7567

DOI: 10.1109/tcsvt.2025.3549953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-08. Verfasst von Yuanliang Xue und 6 weiteren Autor:innen. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: Project of Guangxi Science and Technology, National Natural Science Foundation of China, Guangxi “Young Bagui Scholar” Teams for Innovation and Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The introduction of natural language for vision-language (VL) tracking has been proven to improve performance. However, natural language remains under-explored in existing aerial trackers. Moreover, existing VL trackers ignore the misalignment of language with dynamic target states, which is prominent in complex UAV scenarios. In this work, we present AVLTrack, a flexible framework for aerial vision-language tracking. It consists of three key components, a dynamic sparse learning (DSL) module, an efficient Transformer backbone, and a multi-level language perception (MLP) strategy. First, DSL sparsely connects language and images via dynamic sparse attention, providing accurate multi-modal prompts. To adapt to target state variations, the sparsity in DSL is dynamically adjusted based on semantic information, flexibly highlighting target-specific tokens. Next, the Transformer backbone follows highly parallelized one-stream architectures, allowing efficient multi-modal feature extraction and interaction. Finally, MLP enables the iterative interaction of language and visual information, aiming to utilize language priori to guide the generation of discriminative visual features. Moreover, we construct the DTB70-NLP dataset to facilitate UAV vision-language tracking. Extensive experiments on WebUAV-3M and DTB70-NLP demonstrate the leading performance of AVLTrack compared to existing outstanding trackers while maintaining a high running speed of 80.5 FPS. The dataset and codes are available at https://github.com/xyl-507/AVLTrack.

Förderung

  • Project of Guangxi Science and Technology
  • National Natural Science Foundation of China
  • Guangxi “Young Bagui Scholar” Teams for Innovation and Research Project
  • Research Project of Guangxi Normal University
  • Innovation Project of Guangxi Graduate Education
  • Guangxi Colleges and Universities Key Laboratory of Intelligent Software

Zitieren

APA

Xue, Y., Zhong, B., Jin, G., Shen, T., Tan, L., Li, N., & Zheng, Y. (2025). AVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking. IEEE Transactions on Circuits and Systems for Video Technology, 35(8), 7554-7567. https://doi.org/10.1109/tcsvt.2025.3549953

Vancouver

Xue Y, Zhong B, Jin G, Shen T, Tan L, Li N, et al. AVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(8):7554-7567. doi:10.1109/tcsvt.2025.3549953

BibTeX
@article{Xue2025,
  author = {Xue, Yuanliang and Zhong, Bineng and Jin, Guodong and Shen, Tao and Tan, Lining and Li, Ning and Zheng, Yaozong},
  title = {AVLTrack: Dynamic Sparse Learning for Aerial Vision-Language Tracking},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {8},
  pages = {7554--7567},
  doi = {10.1109/tcsvt.2025.3549953}
}
Kostenlos starten →