EUVIMEDEUVIMED entdecken
Crossref

AFES: Attention-Based Feature Excitation and Sorting for Action Recognition

Mingliang Zhou, Jiahao Li, Xuekai Wei, Jun Luo, Huayan Pu, Wei Wang, Jingyuan He, Zhaowei Shang

IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 5752-5760

DOI: 10.1109/tce.2025.3570181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Mingliang Zhou und 7 weiteren Autor:innen. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Chongqing Talent, Central University Operating Expenses.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Action recognition in virtual reality (VR) is gaining importance as users seek more immersive interactions with virtual environments. Concepts such as augmented reality and the metaverse aim to bridge the gap between the real and virtual worlds, ensuring consistency and efficient feedback for actions in both realms. Previous works in action recognition have typically utilized spatial or temporal convolutions, but these methods often overlook key motion features that are critical for distinguishing between similar action types. In this paper, we propose attention-based feature excitation and sorting (AFES) blocks with hierarchically ordered residual connections to address spatiotemporal information in image sequences for multiscale action recognition tasks. First, we replace the single residual module in existing models with a multiscale learning module that improves feature utilization by adapting to the importance of each feature. Second, we introduce a novel action recognition framework by integrating our multiscale modules into mainstream models, enhancing their ability to recognize actions. Finally, we conduct extensive experiments on widely used datasets, which demonstrate that our multiscale action recognition algorithm outperforms state-of-the-art tracking algorithms.

Förderung

  • National Natural Science Foundation of China
  • Chongqing Talent
  • Central University Operating Expenses
  • Chongqing New YC Project

Zitieren

APA

Zhou, M., Li, J., Wei, X., Luo, J., Pu, H., Wang, W., He, J., & Shang, Z. (2025). AFES: Attention-Based Feature Excitation and Sorting for Action Recognition. IEEE Transactions on Consumer Electronics, 71(2), 5752-5760. https://doi.org/10.1109/tce.2025.3570181

Vancouver

Zhou M, Li J, Wei X, Luo J, Pu H, Wang W, et al. AFES: Attention-Based Feature Excitation and Sorting for Action Recognition. IEEE Transactions on Consumer Electronics. 2025;71(2):5752-5760. doi:10.1109/tce.2025.3570181

BibTeX
@article{Zhou2025,
  author = {Zhou, Mingliang and Li, Jiahao and Wei, Xuekai and Luo, Jun and Pu, Huayan and Wang, Wei and He, Jingyuan and Shang, Zhaowei},
  title = {AFES: Attention-Based Feature Excitation and Sorting for Action Recognition},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {2},
  pages = {5752--5760},
  doi = {10.1109/tce.2025.3570181}
}
Kostenlos starten →