EUVIMEDEUVIMED entdecken
Crossref

Zero-Shot Face Authentication in Multi-User Scenarios Using mmWave Signals

Junlin Yang, Jiadi Yu, Hao Kong, Yanmin Zhu

IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 15267-15279

DOI: 10.1109/tmc.2026.3698153 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Junlin Yang und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Pujiang Program, Science and Technology Commission of Shanghai Municipality project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Face authentication has become an increasingly attractive and prevalent technology in human-computer interaction. Recent works have explored radio frequency (RF) signals for illumination-robust and privacy-preserving face authentication. However, these approaches require all users to undergo compulsory prior registration and cannot effectively handle unregistered users, which restricts their practical applicability in real-world scenarios. In this paper, we present a mm Wave-based m ulti-user face authentication system, m 3 FacePass , which performs zero-shot face authentication in complex multi-user scenarios using a commercial off-the-shelf (COTS) mmWave radar. First, m 3 FacePass collects mmWave signals and reconstructs spatial mappings by generating 3D heatmaps. Based on the 3D heatmaps, m 3 FacePass detects and separates faces in multi-user scenarios through template matching. Then, unique facial features are extracted and transformed to a hypersphere manifold, which reserves feature space for unregistered users. By introducing dummy classifiers in the authentication model, m 3 FacePass optimizes decision boundaries between registered and unregistered users. Furthermore, m 3 FacePass enhances its generalization ability for zero-shot authentication by incorporating pseudo unknowns during model training. Extensive experiments in real-world environments demonstrate that m 3 FacePass achieves an authentication accuracy of 96.6% for registered users and 91.1% for unregistered users in multi-user scenarios.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Pujiang Program
  • Science and Technology Commission of Shanghai Municipality project

Zitieren

APA

Yang, J., Yu, J., Kong, H., & Zhu, Y. (2026). Zero-Shot Face Authentication in Multi-User Scenarios Using mmWave Signals. IEEE Transactions on Mobile Computing, 25(9), 15267-15279. https://doi.org/10.1109/tmc.2026.3698153

Vancouver

Yang J, Yu J, Kong H, Zhu Y. Zero-Shot Face Authentication in Multi-User Scenarios Using mmWave Signals. IEEE Transactions on Mobile Computing. 2026;25(9):15267-15279. doi:10.1109/tmc.2026.3698153

BibTeX
@article{Yang2026,
  author = {Yang, Junlin and Yu, Jiadi and Kong, Hao and Zhu, Yanmin},
  title = {Zero-Shot Face Authentication in Multi-User Scenarios Using mmWave Signals},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {9},
  pages = {15267--15279},
  doi = {10.1109/tmc.2026.3698153}
}
Kostenlos starten →