Visual Sound Source Localization on VGG-SS extended (test)
54.76Localization AccuracySOUPLE
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SOUPLEOGL (Object-Guided Learning)=Without, Training Epochs=502026.03 | 54.76 | 45.81 | 54.22 | |
| SOUPLEOGL (Object-Guided Learning)=Without, Training Epochs=202026.03 | 53.21 | 44.77 | 53 | |
| ACL-SSLOGL (Object-Guided Learning)=Without2026.03 | 49.46 | 40.79 | 49.1 | |
| AudioCLIP2026.03 | 44.15 | 23.79 | 32.8 | |
| AlignmentOGL (Object-Guided Learning)=Without2026.03 | 39.94 | 34.73 | 40.7 | |
| SLAVCTraining Dataset=VGG-Sound 144k, OGL=true2022.08 | 39.8 | 34.46 | 41.5 | |
| FNACOGL (Object-Guided Learning)=Without2026.03 | 39.5 | 23.48 | 33.7 | |
| MarginNCEOGL (Object-Guided Learning)=Without2026.03 | 38.25 | 30.58 | 36.8 | |
| EZ-VSLTraining Dataset=VGG-Sound 144k, OGL=true2022.08 | 37.86 | 27.71 | 34.6 | |
| SLAVCTraining Dataset=VGG-Sound 144k, OGL=false2022.08 | 37.79 | 32.95 | 40 | |
| SLAVCOGL (Object-Guided Learning)=Without2026.03 | 37.79 | 32.95 | 40 | |
| WAV2CLIP2026.03 | 37.71 | 26.67 | 33 | |
| OGLTraining Dataset=VGG-Sound 144k2022.08 | 36.58 | 18.73 | 30.9 | |
| Center PriorTraining Dataset=VGG-Sound 144k2022.08 | 34.16 | — | — | |
| EZ-VSLTraining Dataset=VGG-Sound 144k, OGL=false2022.08 | 31.58 | 24.55 | 30.9 | |
| DSOLTraining Dataset=VGG-Sound 144k2022.08 | 26.87 | 16.84 | 25.6 | |
| DMCTraining Dataset=VGG-Sound 144k2022.08 | 22.63 | 11.53 | 20.3 | |
| CoarsetoFineTraining Dataset=VGG-Sound 144k2022.08 | 21.93 | 0 | 19.8 | |
| Attention10kTraining Dataset=VGG-Sound 144k2022.08 | 14.04 | 6.7 | 13.1 | |
| LVSTraining Dataset=VGG-Sound 144k2022.08 | 10.43 | 5.15 | 9.9 |