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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · VGG-SS | cIoU: 49.46 -> 52.11 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · SoundNet-Flickr | cIoU: 80.80 -> 76.00 | Hurt |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · VPO-SS (single-source localization) | cIoU: 38.1 -> 48.3 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · VPO-MS (single-source localization) | cIoU: 38.2 -> 45.0 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · AVSBench-S4 (single-source localization) | cIoU: 63.5 -> 68.2 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · ADE20K (single-source localization) | cIoU: 45.3 -> 53.8 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · IS3 (single-source localization) | cIoU: 65.9 -> 66.7 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · Extended VGG-SS (robustness) | AP: 40.79 -> 46.72 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · Extended Flickr (robustness) | AP: 76.07 -> 75.21 | No clear effect |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · IS3 (audio-visual segmentation) | mIoU: 37.2 -> 41.1 | Improved |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · IS3 (interactive localization) | IIoU: 43.4 -> 43.2 | No clear effect |
| add LLM-guided object-aware caption-audio alignment loss during training (ablation) | Ours (AV Alignment) · VPO-MS (interactive localization) | IIoU: 28.8 -> 37.4 | Improved |
Closest papers by meaning
- Object-aware Sound Source Localization via Audio-Visual Scene Understanding (CVPR 2025 · similarity 0.92)
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer (AAAI 2024 · similarity 0.91)
- Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence (ECCV 2026 · similarity 0.90)
- A Proposal-Based Paradigm for Self-Supervised Sound Source Localization in Videos (CVPR 2022 · similarity 0.90)
- T-VSL: Text-Guided Visual Sound Source Localization in Mixtures (CVPR 2024 · similarity 0.89)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.89)
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.
