AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Unleashing Vision-Language Semantics for Deepfake Video Detection

Jiawen Zhu, Yunqi Miao, Xueyi Zhang, Jiankang Deng, Guansong Pang

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 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 forgery localization map for local-level authenticity learning to frozen CLIP (ablation)frozen CLIP baseline · CDF-v2 (frame-level)AUROC: 58.3 -> 76.3Improved
add forgery-aware masks into CLIP self-attention (ablation)VLAForge (+T1) · CDF-v2 (frame-level)AUROC: 76.3 -> 82.3Improved
add VLA attention map for local-level reasoning (ablation)VLAForge (+T2) · CDF-v2 (frame-level)AUROC: 82.3 -> 90.8Improved
inject identity prior token into text prompts (ablation)VLAForge (+T3) · CDF-v2 (frame-level)AUROC: 90.8 -> 91.2Improved
inject identity prior token into text prompts (ablation)VLAForge (+T3) · SiT full-face (frame-level)AUROC: 76.8 -> 77.4Improved
add VLA attention loss L_VLA (ablation)VLAForge · CDF-v2 (frame-level)AUROC: 89.1 -> 91.2Improved
add orthogonality loss L_orth on forgery-aware masks (ablation)VLAForge · SiT full-face (frame-level)AUROC: 76.4 -> 77.4Improved
add orthogonality loss L_orth on forgery-aware masks (ablation)VLAForge · VQGAN full-face (video-level)AUROC: 97.9 -> 99.7Improved
use VLAForge instead of ForAdaCLIP-based DFD · DFDC (frame-level)AUROC: 84.3 -> 87.0Improved
use VLAForge instead of ForAda on full-face generated forgeriesCLIP-based DFD · DiT (video-level)AUROC: 67.1 -> 80.3Improved
increase number of query tokens q beyond 128 (ablation)VLAForge · average over five datasetsAUROCHurt
set fusion weight alpha near 0.5 (ablation)VLAForge · average over five datasetsAUROCImproved

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