CGFormer: ViT-Based Network for Identifying Computer-Generated Images With Token Labeling

Weize Quan, Pengfei Deng, Kai Wang 0002, Dong-Ming Yan 0001. CGFormer: ViT-Based Network for Identifying Computer-Generated Images With Token Labeling. IEEE Transactions on Information Forensics and Security, 19:235-250, 2024. [doi]

Abstract

Abstract is missing.