Preprint
Aug 2026
Learning Unified Video and Image Representation for Video Face Forgery Detection
A novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos, which outperforms state-of-theart methods in detecting partially forged videos while introducing no additional computational overhead is proposed.
Haotian Liu, Y. Liu, Guoying Zhao et al.
· 0 citations