AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Break Visual-Linguistic Asymmetry: Unleashing VLM's Cross-Modal Potential for General Face Forgery Detection

Guilin Pang, Yiu-ming Cheung, Ruiqi Li, Weifeng Su

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 0 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 Meta Forgery Adapter (MFA) (ablation)CLIP baseline M1 · Celeb-DF-v2 (trained on FF++ c23)image-level AUC (%): 75.03 -> 87.94Improved
add Asymmetry-Guided Interactor (AGI) (ablation)CLIP baseline M1 · Celeb-DF-v2 (trained on FF++ c23)image-level AUC (%): 75.03 -> 87.92Improved
add AGI on top of MFA (ablation)MFA-only model · Celeb-DF-v2 (trained on FF++ c23)image-level AUC (%): 87.94 -> 92.94Improved
add MFA on top of AGI (ablation)AGI-only model · Celeb-DF-v2 (trained on FF++ c23)image-level AUC (%): 87.92 -> 92.94Improved
add MFA and AGI (ablation)CLIP baseline M1 · DFDC-L (trained on FF++ c23)image-level AUC (%): 72.16 -> 83.60Improved
add AGI on top of MFA (ablation)MFA-only model · DFD (trained on FF++ c23)image-level AUC (%): 92.69 -> 93.85Improved
add AGI on top of MFA (ablation)MFA-only model · Celeb-DF-v2 (trained on FF++ c23)AP (%): 93.76 -> 96.43Mixed
use asymmetric explicit interaction instead of generic symmetric multi-modal methods (vs MMA)Asy-Det · Cross-dataset average (DFD, CDF-v2, DFDC-L)image-level AUC: 0.838 -> 0.901Improved
replace UDD with Asy-Detcross-dataset detector · Celeb-DF-v2 (trained on FF++ c23)image-level AUC: 0.869 -> 0.929Improved
apply generic symmetric interaction (TCP, CoCoOp) to CLIPCLIP-B16 · Cross-dataset average (DFD, CDF-v2, DFDC-L)image-level AUC: 0.775 -> 0.775No clear effect
Asy-Det vs SSG trained on FaceShifter, tested on DFAsy-Det · FaceForensics++ cross-manipulationAUC (%): 94.02 vs 92.22 avgMixed

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