AI Paper Atlas

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

Toward Interactive Sound Source Localization: Better Align Sight and Sound!

Arda Senocak, Hyeonggon Ryu, Junsik Kim, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 13 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 feature alignment (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 39.10 -> 39.94Improved
add multi-view invariance on top of semantic (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 38.75 -> 39.94Improved
add semantic invariance on top of multi-view (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 38.30 -> 39.94Improved
use semantic samples instead of multi-view samples (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 38.30 -> 38.75Improved
add all three components to baseline (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 34.22 -> 39.94Improved
add vision-modality hand-crafted positives (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 34.05 -> 37.72Improved
add audio-modality semantic positives (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 37.01 -> 38.75Improved
increase k in k-NN from 10 to 1000 (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 38.80 -> 39.94Improved
sample randomly from top-1000 instead of fixed same sample (k=1) (ablation)Ours (NN w/ Sup. Pre. Enc.) · VGG-SS (ablation)cIoU: 35.80 -> 38.24Improved
use pretrained vision encoder in NN searchOurs (NN w/ Sup. Pre. Enc.) · VGG-SS (w/o OGL)cIoU: 39.94 -> 41.42Improved
use supervised instead of self-supervised pretrained encoder in NN searchOurs (NN w/ Sup. Pre. Enc.) · VGG-SS (w/o OGL)cIoU: 39.16 -> 39.94Improved
add object-guided localization (OGL) to FNACFNAC · VGG-SScIoU: 39.50 -> 41.85Improved

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