AI Paper Atlas

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

The Sound of Pixels

Hang Zhao, Chuang Gan, Andrew Rouditchenko, Carl Vondrick, Josh McDermott, Antonio Torralba

ECCV 2018 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 445 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
predict a mask instead of regressing the spectrogram (ablation)PixelPlayer · MUSIC synthetic mixturesNSDR: 5.12 -> 8.87Improved
use log-frequency scale instead of linear scale (binary mask) (ablation)PixelPlayer binary mask · MUSIC synthetic mixturesNSDR: 6.94 -> 8.87Improved
use log-frequency scale instead of linear scale (ratio mask) (ablation)PixelPlayer ratio mask · MUSIC synthetic mixturesNSDR: 6.67 -> 8.56Improved
use log-frequency scale instead of linear scale (binary mask) (ablation)PixelPlayer binary mask · MUSIC synthetic mixturesSAR: 11.12 -> 12.28Hurt
use binary mask instead of ratio mask (ablation)PixelPlayer, log scale · MUSIC synthetic mixturesSIR: 13.75 -> 15.02Improved
use binary mask instead of ratio mask (ablation)PixelPlayer, log scale · MUSIC synthetic mixturesSAR: 14.19 -> 12.28Hurt
use binary mask instead of ratio mask (ablation)PixelPlayer · MUSIC human study, sound separationCorrect (%): 39.19 -> 59.11Improved
use binary mask instead of spectral regression (ablation)PixelPlayer · MUSIC human study, sound separationCorrect (%): 18.23 -> 59.11Improved
use binary mask instead of ratio mask (ablation)PixelPlayer · MUSIC human study, visual-sound correspondenceYes responses (%): 54.68 -> 67.58Improved
use binary mask instead of NMF baselinePixelPlayer · MUSIC synthetic mixturesNSDR: 3.14 -> 8.87Improved
use NMF instead of ratio mask model in human studyNMF · MUSIC human study, sound separationCorrect (%): 45.70 -> 39.19Mixed

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