EUVIMEDEUVIMED entdecken
Crossref

AceNet: Attention-Guided Context Enhancement for Imbalanced Action Recognition via RF Signals

Biyun Sheng, Hao Liu, Hui Cai, Yiping Zuo, Jian Zhou, Fu Xiao

IEEE Transactions on Mobile Computing · 2026-07 · 25 (7) · 10455-10470

DOI: 10.1109/tmc.2026.3666114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-07. Verfasst von Biyun Sheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Science Foundation of China, National Science Fund for Distinguished Young Scholars of China, Open Project of the Engineering Research Center of Autonomous Unmanned System Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although radio frequency (RF)-based activity recognition has made significant progress in recent years, the sensing performance will be significantly degraded under class imbalance conditions, especially when minority and majority classes share semantically similar local motion patterns. Traditional data augmentation approaches in the original sample space may cause semantic deviation and meanwhile bring high computational cost. Instead, in this work we turn to address the issue at feature level, in which we focus on how to distinguish highly similar actions and mitigate imbalance-induced decision boundary bias. To tackle these challenges, we present attention-guided context enhancement network (AceNet), which designs a discriminative feature extractor and develops a feature-augmentation based classifier refinement strategy. Specifically, an attention-guided mechanism is presented to dynamically select the most distinctive temporal segments, and a hierarchical Transformer structure is then proposed to characterize both inner-segment micro-dynamics and inter-segment contextual relationships. Moreover, AceNet synthesizes features via Synthetic Minority Over-sampling Technique (SMOTE) to balance feature distribution for each category and then refine the classifier parameters to mitigate class imbalance bias. Comprehensive experiments on two public datasets with different RF modalities demonstrate that AceNet significantly outperforms existing approaches under various levels of data scarcity at a low cost.

Förderung

  • National Science Foundation of China
  • National Science Fund for Distinguished Young Scholars of China
  • Open Project of the Engineering Research Center of Autonomous Unmanned System Technology
  • Ministry of Education
  • China Postdoctoral Special Grant Foundation
  • Open Research Fund of National Mobile Communications Research Laboratory, Southeast University

Zitieren

APA

Sheng, B., Liu, H., Cai, H., Zuo, Y., Zhou, J., & Xiao, F. (2026). AceNet: Attention-Guided Context Enhancement for Imbalanced Action Recognition via RF Signals. IEEE Transactions on Mobile Computing, 25(7), 10455-10470. https://doi.org/10.1109/tmc.2026.3666114

Vancouver

Sheng B, Liu H, Cai H, Zuo Y, Zhou J, Xiao F. AceNet: Attention-Guided Context Enhancement for Imbalanced Action Recognition via RF Signals. IEEE Transactions on Mobile Computing. 2026;25(7):10455-10470. doi:10.1109/tmc.2026.3666114

BibTeX
@article{Sheng2026,
  author = {Sheng, Biyun and Liu, Hao and Cai, Hui and Zuo, Yiping and Zhou, Jian and Xiao, Fu},
  title = {AceNet: Attention-Guided Context Enhancement for Imbalanced Action Recognition via RF Signals},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {7},
  pages = {10455--10470},
  doi = {10.1109/tmc.2026.3666114}
}
Kostenlos starten →