AI Paper Atlas

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

Learning Visual Styles from Audio-Visual Associations

Tingle Li, Yichen Liu, Andrew Owens, Hang Zhao

ECCV 2022 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 16 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
condition on audio instead of YAMNet class labelsaudio-driven image stylization GAN · Into the Wild testAMT score: 1.833 ± 0.042 -> 3.273 ± 0.046Improved
condition on audio instead of manual keyword labelsaudio-driven image stylization GAN · Into the Wild testFID: 38.066 -> 34.139Improved
condition on audio instead of manual keyword labelsaudio-driven image stylization GAN · Into the Wild testCLIP score: 0.236 -> 0.238No clear effect
use audio instead of a random style image (AdaIN)audio-driven image stylization GAN · Into the Wild testAVC: 0.812 -> 0.820Improved
use audio instead of keyword labels for sunny target scenesaudio-driven image stylization GAN · Into the Wild test, Sunny-to-RainyAVC: 0.827 -> 0.831Improved
add NCE contrastive loss instead of cycle-consistency (ablation)audio-driven image stylization GAN · Into the Wild test (ablation)FID: 35.244 -> 34.139No clear effect
add early-fusion discriminator instead of late fusion (ablation)audio-driven image stylization GAN · Into the Wild test (ablation)FID: 54.025 -> 34.139Improved
add identity loss (ablation)audio-driven image stylization GAN · Into the Wild test (ablation)FID: 41.019 -> 34.139Improved
add identity loss (ablation)audio-driven image stylization GAN · Into the Wild test (ablation)AVC: 0.810 -> 0.820Improved
initialize audio network with SeLaVi pre-trainingaudio-driven image stylization GAN · Into the Wild test (pre-training)FID: 34.139 -> 32.882Improved
initialize audio network with Wav2CLIP pre-training instead of SeLaViaudio-driven image stylization GAN · Into the Wild test (pre-training)FID: 32.882 -> 30.334Improved

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