AI Paper Atlas

Research map / Video / Video segmentation and tracking

Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection

Dat Nguyen, Marcella Astrid, Anis Kacem, Enjie Ghorbel, Djamila Aouada

ICCV 2025 · Video › Video segmentation and tracking · approach: Deepfake video detection · 21 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 SBV pseudo-fake training data (ablation)TimeSformer baseline · Cross-dataset avg (FF++ c23)AUC (%): 63.2 -> 85.1Improved
add vulnerability-driven Cutout (ablation)TimeSformer + SBV · Cross-dataset avg (FF++ c23)AUC (%): 85.1 -> 85.2No clear effect
add spatial branch g (ablation)TimeSformer + SBV + V-CutOut · Cross-dataset avg (FF++ c23)AUC (%): 85.2 -> 85.7Improved
add temporal branch h (ablation)TimeSformer + SBV · Cross-dataset avg (FF++ c23)AUC (%): 85.1 -> 86.7Improved
add V-CutOut and g to SBV + h (ablation)TimeSformer + SBV + h · Cross-dataset avg (FF++ c23)AUC (%): 86.7 -> 87.8Improved
add Consistent Synthesized Parameters (CSP) (ablation)Stacked SBIs · CDFAUC (%): 48.4 -> 84.1Improved
add Landmark Interpolation (LI) (ablation)SBV with CSP · CDFAUC (%): 84.1 -> 90.7Improved
use raw c0 data instead of c23 for SBV trainingSBV · CDFAUC (%): 90.7 -> 94.9Improved
increase number of frames T from 4 to 16FakeSTormer · CDFAUC (%): 92.4 -> 92.8Improved
loss weights 0.8/100/0.2 instead of 0.9/1/0.1 (ablation)FakeSTormer · Cross-dataset avg (FF++ c23)AUC (%): 85.1 -> 87.8Improved
MeanStd instead of MinMax normalization of temporal GT (ablation)FakeSTormer · Cross-dataset avg (FF++ c23)AUC (%): 84.8 -> 87.8Improved
MeanStd instead of unnormalized 3D Gaussian (ablation)FakeSTormer · Cross-dataset avg (FF++ c23)AUC (%): 85.2 -> 87.8Improved

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