
JJ
Jiahua Jiang, Jinglai Li, Jianru Zhang, Jin Zhu
· 1 min read
ResearcharXiv cs.CV
Learning Reconstruction Errors as Spatiotemporal Evidence for AI-Generated Video Detection
arXiv:2611.26116v1 Announce Type: new
Abstract: The proliferation of AI-generated videos has raised growing concerns about misinformation, fraud, and potential societal risks, creating an urgent need for detection. Reconstruction-error-based methods have shown strong empirical performance for AI-generated image detection by exploiting discrepancies between an input and its reconstructed version. Their extension to video detection, however, faces two challenges: (i) a fixed reconstructor is not optimized for the detection objective and may yield weak discriminative signals; and (ii) an additional raw-video feature stream is often introduced to model temporal dependencies, increasing architectural overhead. To address these challenges, we develop a detector that learns and exploits reconstruction errors as a unified source of spatiotemporal evidence. First, we jointly optimize a reconstructor and the downstream classifier to produce reconstruction errors that are more informative for detecting AI-generated videos. Second, we show that consecutive reconstruction errors alone carry temporal evidence, and thus a 3D convolution over them captures spatiotemporal evidence without a raw-video stream. Extensive experiments on over 30 existing AI-video generators demonstrate competitive performance against baselines.
Original source
This story was published by arXiv cs.CV and written by Jiahua Jiang, Jinglai Li, Jianru Zhang, Jin Zhu. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


