AI Paper Atlas

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

Joint Audio-Visual Deepfake Detection

Yipin Zhou, Ser-Nam Lim

ICCV 2021 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 240 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
late-fuse video and audio streams (ablation)Indp · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 95.83 -> 94.25Hurt
add sync-stream with central connections at low and high layers (no attention) (ablation)Late-fuse · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 94.25 -> 97.02Improved
add sync-stream (central connections) (ablation)Indp · DFDC (audiovisual)whole-video accuracy (%): 89.36 -> 91.01Improved
use inter-attention instead of inter+intra attention (ablation){2+1}-streams · FF (FaceForensics++ audiovisual)audio-stream accuracy (%): 94.25 -> 96.03Improved
use inter-attention instead of joint attention (ablation){2+1}-streams · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 96.23 -> 97.62Improved
add inter-attention to sync-stream (ablation){2+1}-streams · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 97.02 -> 97.62Improved
add attention to sync-stream (ablation){2+1}-streams · DFDC (audiovisual)whole-video accuracy (%): 91.01 -> 90.84No clear effect
freeze independently trained video and audio streams (Fix-indp-audvid) (ablation){2+1}-streams Inter · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 97.62 -> 96.63Hurt
freeze independently trained streams in late-fuse model (ablation)Late-fuse · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 94.25 -> 94.84Improved
connect audio and visual features at more lower layers (cnt-1234 vs late-fuse) (ablation){2+1}-stream · FF (FaceForensics++ audiovisual)whole-video accuracy (%)Improved
train with shuffled (unpaired) audio (ablation){2+1}-streams+att · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 97.62 -> 95.44Hurt
train with shuffled audio versus independent streamsIndp · FF (FaceForensics++ audiovisual)whole-video accuracy (%): 95.83 -> 95.44No clear effect

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