| Benchmark | Model | Rank | Results |
|---|---|---|---|
| referring-expression-segmentation-on-refer-youtube-vos-2021-public-validation | SPOT-13B | – | J&F: 71.8 |
| referring-video-object-segmentation-on-mevis | SPOT-13B | – | J&F: 51.2 |
| referring-video-object-segmentation-on-revos | SPOT-13B | – | J&F: 54.8 |