Audio-to-image retrieval on SSW60
70.47mAPBioLingual-FT
Evaluation Results
| Method | Links | |
|---|---|---|
| BioLingual-FT2026.01 | 70.47 | |
| Text Embeddings Mapping2026.01 | 51.39 | |
| Cascaded Zero-Shotinput_modality=Image+Audio2026.01 | 39.85 | |
| Random Projection2026.01 | 3.79 |
| Method | Links | |
|---|---|---|
| BioLingual-FT2026.01 | 70.47 | |
| Text Embeddings Mapping2026.01 | 51.39 | |
| Cascaded Zero-Shotinput_modality=Image+Audio2026.01 | 39.85 | |
| Random Projection2026.01 | 3.79 |