Referring Audio-Visual Segmentation on Ref-AVS 1.0
0.23S-scoreSAM2-LOVE
Evaluation Results
| Method | Links | |
|---|---|---|
| SAM2-LOVEInput Modality=Audio + Text2025.06 | 0.23 | |
| AVSBenchInput Modality=Audio + Text2025.06 | 0.208 | |
| GAVSInput Modality=Audio + Text2025.06 | 0.19 | |
| R2VOSInput Modality=Text + Audio2025.06 | 0.183 | |
| ReferFormerInput Modality=Text + Audio2025.06 | 0.176 | |
| AVSegFormerInput Modality=Audio + Text2025.06 | 0.171 | |
| EEMCInput Modality=Audio + Text2025.06 | 0.007 |