AIGC video detection based on the fusion of spatial-frequency-optical flow multimodal features
A multi-modal framework for AIGC video forgery detection tasks, named Cross-Attention based Video Forgery Detector (CrossAtt-VFD), based on joint multi-view analysis of content, and introduces a dual-branch architecture that simultaneously extracts spatial-frequency and optical-flow features.
Sheng Hong, Xuan-Qi Wang, Chang Zhang et al.
· Journal of Systems Engineeri... · 18 citations