AI Paper Atlas

Research map / Video / Video generation

Real Data Lies: Unveiling and Closing the Quality Shortcut in Generalizable AI-Generated Video Detection

Ziyuan Fang, Tianyi Wei, Guanjie Wang, Weiming Zhang, Nenghai Yu, Wenbo Zhou

ICML 2026 · Video › Video generation · approach: Autoregressive long video generation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Kinetics-400 + Pika training pair with quality-matched InternVid-AES + Pika (ablation)VideoMAEv2-B · GenVideo revised protocol, Overall MeanAUC (%): 81.70 -> 87.78Improved
quality-aligned training data (InternVid-AES + Pika) instead of Kinetics-400 + Pika (ablation)DINOv3-L · GenVideo revised protocol, Overall MeanAUC (%): 87.09 -> 86.59Hurt
quality-aligned training data (InternVid-AES + Pika) instead of Kinetics-400 + Pika (ablation)SAFE · GenVideo revised protocol, Overall MeanAUC (%): 77.24 -> 77.33No clear effect
add quality-aware data expansion (LQ and UHQ real/fake pairs) on top of aligned dataDINOv2-L · GenVideo revised protocol, Overall MeanAUC (%): 89.81 -> 94.83Improved
add quality-aware data expansion on top of aligned dataSAFE · GenVideo revised protocol, Overall MeanAUC (%): 77.33 -> 85.15Improved
add LQ expansion (Kinetics-400 + OpenSora) only (ablation)VideoMAEv2-B Aligned · GenVideo revised protocol, Overall MeanAUC (%): 87.78 -> 92.56Improved
add UHQ expansion (OpenVidHD + DynamiCrafter) only (ablation)VideoMAEv2-B Aligned · GenVideo revised protocol, Overall MeanAUC (%): 87.78 -> 90.86Improved
add both LQ and UHQ expansion (ablation)VideoMAEv2-B Aligned · GenVideo revised protocol, Overall MeanAUC (%): 87.78 -> 93.39Improved
quality-matched aligned set (1x data) versus 3x larger biased set (ablation)VideoMAEv2-B · 9 real datasets, Mean* (unseen datasets)AUC (%): 84.88 -> 86.15Improved
3x scale up of biased training data (Biased++) (ablation)VideoMAEv2-B · 9 real datasets, Overall MeanAUC (%): 81.88 -> 89.40Improved
expanded quality-aware data versus Biased++ at equivalent scale (ablation)VideoMAEv2-B · 9 real datasets, Overall MeanAUC (%): 89.40 -> 94.23Improved
train on high-quality real data matching Pika (InternVid-AES) instead of low-quality (Youku-mPLUG) or ultra-HQ (OpenVidHD) (ablation)VideoMAEv2-B · Overall Mean over 9 real test datasetsAUC (%): 81.88 (Kinetics-400), 78.48 (Youku-mPLUG), 81.23 (OpenVidHD) -> 88.35 (InternVid-AES)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy