Skip to content

Semantics-aware contrastive and explicitly disentangled representations for AI-generated video detection

Semantic-aware Contrasting with Explicitly Disentangled Representations for AI-Generated Video Detection

arXiv· arXiv:2611.24038· Jiaquan Yu, Jingyi Xie, Zeyu Zhang, Yunhang Qian, Xiaobin Hu, Jiawei Liu·Indexed by this site · 12 hr ago· Originally publishedAttacks· Its place in the scan record →
AI summary

The paper proposes an AI-generated video detection dataset SAVGE (2,369,822 videos) and a model-agnostic training framework EDSC. SAVGE uses real video captions as prompts to generate fake videos, forming real-fake semantic groups; EDSC suppresses semantic information in the artifact branch, making the detector focus on generation artifacts. On SAVGE and GenVideo, EDSC improves most backbone-metric combinations, enhancing robustness and cross-dataset generalization under challenging settings.

Read originalarxiv.org