一作ACL 2026Poster· Natural Language Processing
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline
Jingchun Lian · Lingyu Liu · Yaxiong Wang · Yujiao Wu · Lianwei Wu · Li Zhu · Zhedong Zheng
摘要
Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. To address this, we introduce Forgery Attribution Report Generation , a new multimodal task designed to provide po...