EUVIMEDEUVIMED entdecken
Crossref

PMCF: A Progressive Multi-Level Collaborative Framework for Face Forgery Detection

Hongning Li, Zengzhang Li, Haijie Du, Jiawei Zhang, Xiaodan Song, Qingqi Pei

IEEE Signal Processing Letters · 2026 · 33 · 2979-2983

DOI: 10.1109/lsp.2026.3713102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Hongning Li und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of deepfake image generation poses significant threats to information security and social trust, with forgery artifacts exhibiting multi-scale characteristics from micro-level noise to macro-level semantic anomalies.Existing detection methods are limited by single-scale feature extraction and inefficient fusion due to semantic gaps between deep and shallow features.To address these issues, this letter proposes a Progressive Multi-Level Collaborative Framework (PMCF) comprising a multi-granularity collaborative attention (MGCA) module and a multi-level attention fusion (MLAF) module. MGCA uses three parallel Transformer branches to model pixel-level textures, local structures, and global semantics, while MLAF integrates a feature pyramid, joint attention, and progressive bidirectional fusion for effective feature alignment. Experimental results show consistent AUC improvements over comparative methods across multiple datasets.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, H., Li, Z., Du, H., Zhang, J., Song, X., & Pei, Q. (2026). PMCF: A Progressive Multi-Level Collaborative Framework for Face Forgery Detection. IEEE Signal Processing Letters, 33, 2979-2983. https://doi.org/10.1109/lsp.2026.3713102

Vancouver

Li H, Li Z, Du H, Zhang J, Song X, Pei Q. PMCF: A Progressive Multi-Level Collaborative Framework for Face Forgery Detection. IEEE Signal Processing Letters. 2026;33:2979-2983. doi:10.1109/lsp.2026.3713102

BibTeX
@article{Li2026,
  author = {Li, Hongning and Li, Zengzhang and Du, Haijie and Zhang, Jiawei and Song, Xiaodan and Pei, Qingqi},
  title = {PMCF: A Progressive Multi-Level Collaborative Framework for Face Forgery Detection},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {2979--2983},
  doi = {10.1109/lsp.2026.3713102}
}
Kostenlos starten →