ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection 事件

ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection arXiv:2606.04706v1 Announce Type: new Abstract: AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection is therefore essential for multimedia forensics, yet remains challenging due to the need to capture spatial artifacts, temporal dynamics, and generalize to evolving generative models