AI Paper Atlas

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

Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching

Arsha Nagrani, Samuel Albanie, Andrew Zisserman

CVPR 2018 · 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
use dynamic face videos instead of still face imagesCross-modal CNN (V-F) · Cross-modal matching, total test setIdentification accuracy: 81.0 -> 84.3Improved
use dynamic face videos instead of still face imagesCross-modal CNN (F-V) · Cross-modal matching, total test setIdentification accuracy: 79.5 -> 82.9Improved
remove gender, age, and nationality variation from test pairsCross-modal CNN (V-F) · Static testIdentification accuracy: 81.0 -> 63.9Hurt
remove gender, age, and nationality variation from test pairsCross-modal CNN (V-F) · Dynamic testIdentification accuracy: 84.3 -> 67.4Hurt
use one dynamic image instead of RGB frames (ablation)Dynamic matching F-V · Dynamic testIdentification accuracy: 79.2 ± 0.1 -> 76.9 ± 0.6Hurt
use multiple dynamic images instead of one per face-track (ablation)Dynamic matching F-V · Dynamic testIdentification accuracy: 76.9 ± 0.6 -> 79.9 ± 0.2Improved
add multiple dynamic images to RGB frame inputs (ablation)Dynamic matching F-V · Dynamic testIdentification accuracy: 79.2 ± 0.1 -> 84.3 ± 0.2Improved
add one dynamic image to RGB frame inputs (ablation)Dynamic matching F-V · Dynamic testIdentification accuracy: 79.2 ± 0.1 -> 82.4 ± 0.3Improved
replace one dynamic image with multiple dynamic images in RGB fusion (ablation)Dynamic matching F-V · Dynamic testIdentification accuracy: 82.4 ± 0.3 -> 84.3 ± 0.2Improved
use dynamic images without RGB face inputs (ablation)Dynamic matching F-V · Dynamic testIdentification accuracy: 79.9 ± 0.2Improved

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