SOURCE-LINKED INTELLIGENCE

TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Recent advances in generative video models have enabled the synthesis of visually realistic content, posing significant challenges to synthetic video detection. Existing detectors often rely on appearance artifacts, semantic inconsistencies, and temporal patterns that may be generator-specific, limitating generalization to unseen synthesis models. We investigate whether responses to a pretrained generative model provide more transferable forensic cues. Our key observation is that real and AI-generated videos exhibit distinct \emph{velocity responses} under a pretrained Flow Matching video mode

Read original source ↗ Open in workspace

recordType

paper

region

Global