Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection

arXiv:2607.15321v1 Announce Type: new Abstract: AI-generated videos (AIGVs) typically contain subtle temporal artifacts that arise from inter-frame inconsistencies rather than within individual frames. A detector that captures such artifacts should therefore benefit from video pretrained backbones over image only ones. In practice, however, video backbones with standard global readouts often fail to outperform strong image pretrained probes on AIGV benchmarks. We attribute this gap to excessive ...