AI Paper Atlas

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

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

Kim Sung-Bin, Arda Senocak, Hyunwoo Ha, Andrew Owens, Tae-Hyun Oh

CVPR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 39 citations (OpenAlex)

Read the paper

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
Replace the image encoder input with an audio encoder while retaining the same generatorSound2Scene · VGGSound (50 classes)R@1: 30.06 -> 40.71Improved
Replace the image encoder input with an audio encoder while retaining the same generatorSound2Scene · VGGSound (50 classes)FID: 16.11 -> 17.97Hurt
Replace the image encoder input with an audio encoder while retaining the same generatorSound2Scene · VEGASR@1: 46.60 -> 57.44Improved
Generate images rather than retrieve them from the training-image databaseSound2Scene · VGGSound (50 classes)R@1: 51.28 -> 40.71Hurt
Generate images rather than retrieve them from the training-image databaseSound2Scene · VGGSound (50 classes)R@5: 80.37 -> 77.36Hurt
Use symmetric InfoNCE rather than L2 feature matching (ablation)Sound2Scene · VGGSound (50 classes)R@1: 18.21 -> 40.71Improved
Use symmetric InfoNCE rather than one-way InfoNCE (ablation)Sound2Scene · VGGSound (50 classes)R@1: 31.63 -> 40.71Improved
Add sound-source-localization frame selection (ablation)Sound2Scene · VGGSound (50 classes)R@1: 37.20 -> 40.71Improved
Increase audio duration from 1 second to 5 seconds (ablation)Sound2Scene · VGGSound (50 classes)R@1: 35.85 -> 38.24Improved
Increase audio duration from 5 seconds to 10 seconds (ablation)Sound2Scene · VGGSound (50 classes)R@1: 38.24 -> 40.71Improved
Increase audio duration from 1 second to 10 seconds (ablation)Sound2Scene · VGGSound (50 classes)FID: 19.05 -> 17.97Improved
Increase audio duration from 1 second to 10 seconds (ablation)Sound2Scene · VGGSound (50 classes)IS: 17.87 -> 19.46Improved

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