AI RESEARCH
ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity
arXiv CS.CV
•
ArXi:2604.04029v1 Announce Type: new AI-generated videos (AIGVs) have achieved unprecedented photorealism, posing severe threats to digital forensics. Existing AIGV detectors focus mainly on localized artifacts or short-term temporal inconsistencies, thus often fail to capture the underlying generative logic governing global temporal evolution, limiting AIGV detection performance. In this paper, we identify a distinctive fingerprint in AIGVs, termed anomalous temporal self-similarity