EUVIMEDEUVIMED entdecken
Crossref

Cross-Attention Based Two-Branch Networks for Document Image Forgery Localization in the Metaverse

Yalin Song, Wenbin Jiang, Xiuli Chai, Zhihua Gan, Mengyuan Zhou, Lei Chen

ACM Transactions on Multimedia Computing, Communications, and Applications · 28.02.2025 · 21 (2) · 1-24

DOI: 10.1145/3686158 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 30.12.2024. Verfasst von Yalin Song und 5 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Project of Henan Province, Key Scientific Research Projects of Colleges and Universities of Henan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the Metaverse has garnered significant attention in social and Metahuman realms, showcasing substantial value and immense developmental potential through its integration of virtual and real worlds. However, this integration has also raised security concerns. For instance, in digital image forensics, the malicious dissemination of false images by wrongdoers could result in serious consequences and the propagation of misinformation. This article presented a novel two-branch network (abbreviated as CAFTB-Net) to detect and localize the forged regions of document images in the Metaverse. One branch extracts manipulation trace directly from spatial information, e.g., unnatural smears, anomalies between pixels. The other branch employs an SRM filter to transform the input image from the color domain into the noise domain, effectively extracting anomalies, such as global noise inconsistencies from the noise domain. Compared to spatial domain features, the discontinuity of forgery traces within the noise domain aids the network in authenticating the document image. The two branches extract local and global features in the forged document images. Finally, we propose a cross-attention module to fuse local spatial features and global noise features. Extensive experimental results demonstrate that the proposed network achieves F1 scores of 0.819 and 0.948 on the SACP and ICDAR datasets, respectively, with AUC scores of 0.933 and 0.764, outperforming some of the state-of-the-art algorithms.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Project of Henan Province
  • Key Scientific Research Projects of Colleges and Universities of Henan Province
  • Natural Science Foundation Project of Henan Province
  • Pre-research Project of Song Shan Laboratory

Zitieren

APA

Song, Y., Jiang, W., Chai, X., Gan, Z., Zhou, M., & Chen, L. (2025). Cross-Attention Based Two-Branch Networks for Document Image Forgery Localization in the Metaverse. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(2), 1-24. https://doi.org/10.1145/3686158

Vancouver

Song Y, Jiang W, Chai X, Gan Z, Zhou M, Chen L. Cross-Attention Based Two-Branch Networks for Document Image Forgery Localization in the Metaverse. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(2):1-24. doi:10.1145/3686158

BibTeX
@article{Song2025,
  author = {Song, Yalin and Jiang, Wenbin and Chai, Xiuli and Gan, Zhihua and Zhou, Mengyuan and Chen, Lei},
  title = {Cross-Attention Based Two-Branch Networks for Document Image Forgery Localization in the Metaverse},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2025},
  volume = {21},
  number = {2},
  pages = {1--24},
  doi = {10.1145/3686158}
}
Kostenlos starten →