Research map / Label-efficient and robust learning / Self-supervised and contrastive
Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FNS using both audio and image adjacency matrices (ablation) | NCE audio-visual localization · Flickr test (VGG-SS 10k train) | CIoU (%): 77.91 -> 84.33 | Helped |
| Add FNS using both audio and image adjacency matrices (ablation) | NCE audio-visual localization · VGG-SS test (VGG-SS 10k train) | CIoU (%): 33.93 -> 36.92 | Helped |
| Add TNE region-wise true-negative regularization (ablation) | NCE audio-visual localization · Flickr test (VGG-SS 10k train) | CIoU (%): 77.91 -> 81.12 | Helped |
| Add TNE region-wise true-negative regularization (ablation) | NCE audio-visual localization · VGG-SS test (VGG-SS 10k train) | CIoU (%): 33.93 -> 36.04 | Helped |
| Use FNAC instead of EZ-VSL + OGL | Audio-visual localization · Flickr test (Flickr 144k train) | CIoU (%): 83.13 -> 78.71 | Hurt |
| Use FNAC instead of EZ-VSL + OGL | Audio-visual localization · VGG-SS test (Flickr 144k train) | CIoU (%): 41.01 -> 33.93 | Hurt |
| Apply FNAC at batch size 64 or less | Audio-visual localization baseline · Flickr and VGG-SS | localization performance | Mixed |
| Increase batch size while using FNAC | Audio-visual localization baseline · Flickr and VGG-SS | localization performance | Helped |
Closest papers by meaning
- Improving Sound Source Localization with Joint Slot Attention on Image and Audio (CVPR 2025 · similarity 0.89)
- Object-aware Sound Source Localization via Audio-Visual Scene Understanding (CVPR 2025 · similarity 0.89)
- T-VSL: Text-Guided Visual Sound Source Localization in Mixtures (CVPR 2024 · similarity 0.88)
- CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment (CVPR 2025 · similarity 0.87)
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer (AAAI 2024 · similarity 0.86)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.86)
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.