AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatial-Temporal Forgery Trace based Forgery Image Identification

Yilin Wang, Zunlei Feng, Jiachi Wang, Hengrui Lou, Binjia Zhou, Jie Lei, Mingli Song, Yijun Bei

ICCV 2025 · Video › Video segmentation and tracking · approach: Deepfake video detection · 4 citations (OpenAlex)

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
add temporal prior correlation module (ablation)STFT · DALL·E 3 (DeepFaceGen)AUC: 86.28 -> 92.02Improved
add spatial correlation module (ablation)STFT · DALL·E 3 (DeepFaceGen)AUC: 79.71 -> 92.02Improved
add frequency-enhanced attention module (ablation)STFT · DALL·E 3 (DeepFaceGen)AUC: 89.75 -> 92.02Improved
use 20 diffusion sampling steps instead of 10, 15, 25 or 30 (ablation)STFT · GenImage / DeepFaceGenaccuracy: best at 20 stepsImproved
use 3x8x8 latent resolution instead of lower (3x4x4) or higher (ablation)STFT · GenImage / DeepFaceGenaccuracy: best at 3 × 8 × 8Improved
STFT versus DRCT on cross-subset generalizationSTFT · GenImage (cross-subset)accuracy: Midjourney 89.3 -> 92.3; BigGAN 84.0 -> 85.6Improved
STFT versus DIRE/DRCT on non-face imagesSTFT · LSUN Cat/Horse/BedroomAUC: 74.48 -> 90.32 (Cat, vs DRCT)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