AI-Generated Video Detection via Spatio-Temporal Anomaly Learning

arXiv:2403.16638v1 Announce Type: new
Abstract: The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent videos to spread false information. This letter proposes an effective AI-generated video detection (AIGVDet) scheme by capturing the forensic traces with a two-branch spatio-temporal convolutional neural network (CNN). Specifically, two ResNet sub-detectors are learned separately for identifying the anomalies in spatical and optical flow domains, respectively. Results of such sub-detectors are fused …

ai-generated video anomaly arxiv cs.cr cs.cv detection generated temporal type via video