Single Sound Source Localization on MUSIC Solo (test)
98.5IoU@0.5Generation-Analysis-Refinement
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Generation-Analysis-RefinementN (Number of iterations in Stage 2)=52026.04 | 98.5 | 80.6 | 78.2 | |
| Generation-Analysis-RefinementN (Number of iterations in Stage 2)=32026.04 | 96.2 | 78.9 | 76.9 | |
| OA-SSL2026.04 | 71.1 | 79.8 | 60.9 | |
| Qwen2.5-Omni2026.04 | 67.8 | 62.7 | 60.7 | |
| Proposed MethodVisual Backbone=ResNet-18, Audio Backbone=ResNet-182024.03 | 62.1 | 77.4 | 59.4 | |
| NoPrior2026.04 | 62.1 | 77.4 | 59.4 | |
| AVGN2024.03 | 58.1 | 77.2 | 48.5 | |
| AVGN2026.04 | 58.1 | 77.2 | 48.5 | |
| DSOL2024.03 | 51.4 | — | 43.7 | |
| DSOL2026.04 | 51.4 | — | 43.7 | |
| EZ-VSL2024.03 | 45.8 | 71.5 | 41.2 | |
| EZ-VSL2026.04 | 45.8 | 71.5 | 41.2 | |
| LVS2024.03 | 41.9 | 70.6 | 40.3 | |
| LVS2026.04 | 41.9 | 70.6 | 40.3 | |
| Attention10k2024.03 | 37.2 | — | 38.7 | |
| Attention 10k2026.04 | 37.2 | — | 38.7 | |
| CoarseToFine2024.03 | 33.6 | 70.7 | 39.8 | |
| CoarseToFIne2026.04 | 33.6 | 70.7 | 39.8 | |
| MiniCPM-o2026.04 | 32.8 | 26.2 | 20.1 | |
| Mix-and-Localize2024.03 | 30.5 | 68.6 | 40.8 | |
| Mix-and-Localize2026.04 | 30.5 | 68.6 | 40.8 | |
| DMC2024.03 | 29.1 | — | 38 | |
| DMC2026.04 | 29.1 | — | 38 | |
| InteractiveOmni2026.04 | 29 | 36.7 | 33.2 | |
| OTS2024.03 | 26.1 | 69.3 | 35.8 | |
| OTS2026.04 | 26.1 | 69.3 | 35.8 |