Sound Localization on MUSIC-Solo 1.0 (test)
68.5IoU@0.5T-VSL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| T-VSLMethod Category=Ours2024.04 | 68.5 | 88.2 | 60.1 | |
| AlignmentMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 66.4 | 86.1 | 57.2 | |
| AVGNMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 65.8 | 85.4 | 56.9 | |
| FNACMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 64.5 | 84.6 | 56.4 | |
| MarginNCEMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 63.3 | 83.1 | 55.2 | |
| AudioCLIPMethod Category=CLIP-Based Baseline Methods, Pre-trained Encoders=AudioCLIP2024.04 | 63.1 | 83.8 | 55.7 | |
| DSOLMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 62.7 | — | 54.6 | |
| Mix-and-LocalizeMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 59.9 | 78.9 | 52.7 | |
| Wav2CLIPMethod Category=CLIP-Based Baseline Methods, Pre-trained Encoders=AudioCLIP2024.04 | 59.9 | 78.9 | 51.2 | |
| EZ-VSLMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 58.7 | 78.4 | 51.1 | |
| AVGN2023.03 | 58.1 | 77.2 | 48.5 | |
| CoarsetoFineMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 58.1 | 76.3 | 49.7 | |
| OTSMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 57.8 | 76.2 | 48.9 | |
| LVSMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 57.1 | 76.1 | 49.3 | |
| DSOL2023.03 | 51.4 | — | 43.7 | |
| EZ-VSL2023.03 | 45.8 | 71.5 | 41.2 | |
| LVS2023.03 | 41.9 | 70.6 | 40.3 | |
| Attention10k2023.03 | 37.2 | — | 38.7 | |
| CoarsetoFine2023.03 | 33.6 | 70.7 | 39.8 | |
| Mix-and-Localize2023.03 | 30.5 | 68.6 | 40.8 | |
| DMC2023.03 | 29.1 | — | 38 | |
| OTS2023.03 | 26.1 | 69.3 | 35.8 |