AI Paper Atlas

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

Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications

Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming–Hsuan Yang, In So Kweon

TPAMI 2019 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 60 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
add 2.5k supervised samples to unsupervised 10k training (ablation)sound localization network · Flickr-SoundNet (softmax)cIoU: 43.6 -> 82.8Improved
train on 144k unsupervised pairs instead of 10k (ablation)unsupervised network · Flickr-SoundNet (softmax)cIoU: 43.6 -> 66.0Improved
add unsupervised 10k loss to supervised 2.5k (ablation)supervised network · Flickr-SoundNet (softmax)cIoU: 80.4 -> 82.8Improved
add unsupervised 10k loss to supervised 2.5k (ablation)supervised network · Flickr-SoundNet (ReLU+softmax)cIoU: 82.0 -> 84.0Improved
add 144k unsupervised pairs instead of 10k to semi-supervised model (ablation)semi-supervised network · Flickr-SoundNet (ReLU+softmax)cIoU: 84.0 -> 84.4No clear effect
increase supervised samples from 0.10k to 1.00k with 10k unsupervised (ablation)semi-supervised network · Flickr-SoundNet (ReLU+softmax)cIoU: 77.2 -> 82.4Improved
increase supervised samples beyond 1.00k to 2.50k (ablation)semi-supervised network · Flickr-SoundNet (ReLU+softmax)cIoU: 82.4 -> 84.0No clear effect
add ReLU to attention (suppress negative correlation) for unsupervised 144k (ablation)unsupervised network · Flickr-SoundNetcIoU: 66.0 -> 52.4Hurt
add ReLU to attention for supervised 2.5k (ablation)supervised network · Flickr-SoundNetcIoU: 80.4 -> 82.0Improved
add ReLU to attention (ablation)localization network · ambient sounds (qualitative)response to ambient soundImproved
set loss weight Unsup.=0.5, Sup.=0.5 versus Unsup.=0.1, Sup.=0.9 (ablation)semi-supervised network · Unsup. 144k + Sup. 0.5kcIoU: 82.8 -> 85.2Improved
raise unsupervised loss weight to 0.9 (ablation)semi-supervised network · Unsup. 144k + Sup. 0.5kcIoU: 85.2 -> 83.2Hurt

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