AI Paper Atlas

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

Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization

Sooyoung Park, Arda Senocak, Joon Son Chung

IJCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 2 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 LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · VGG-SScIoU: 49.46 -> 52.11Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · SoundNet-FlickrcIoU: 80.80 -> 76.00Hurt
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · VPO-SS (single-source localization)cIoU: 38.1 -> 48.3Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · VPO-MS (single-source localization)cIoU: 38.2 -> 45.0Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · AVSBench-S4 (single-source localization)cIoU: 63.5 -> 68.2Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · ADE20K (single-source localization)cIoU: 45.3 -> 53.8Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · IS3 (single-source localization)cIoU: 65.9 -> 66.7Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · Extended VGG-SS (robustness)AP: 40.79 -> 46.72Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · Extended Flickr (robustness)AP: 76.07 -> 75.21No clear effect
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · IS3 (audio-visual segmentation)mIoU: 37.2 -> 41.1Improved
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · IS3 (interactive localization)IIoU: 43.4 -> 43.2No clear effect
add LLM-guided object-aware caption-audio alignment loss during training (ablation)Ours (AV Alignment) · VPO-MS (interactive localization)IIoU: 28.8 -> 37.4Improved

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