| referring-video-object-segmentation-on-long-rvos | VideoSEG-O3-4B | #1 | J&F: 57.4 |
| referring-video-object-segmentation-on-long-rvos | VideoSEG-O3-2B | #2 | J&F: 54.8 |
| referring-expression-segmentation-on-refer-youtube-vos-2021-public-validation | VideoSEG-O3-4B | #2 | J&F: 74.1 |
| referring-expression-segmentation-on-refer-youtube-vos-2021-public-validation | VideoSEG-O3-2B | #11 | J&F: 70.5 |
| referring-video-object-segmentation-on-ref-davis17 | VideoSEG-O3-2B | #3 | J&F: 80.0 |
| referring-video-object-segmentation-on-ref-davis17 | VideoSEG-O3-4B | #6 | J&F: 79.4 |
| referring-video-object-segmentation-on-revos | VideoSEG-O3-4B | #4 | J&F: 67.7J: 65.0F: 70.4 |
| referring-video-object-segmentation-on-revos | VideoSEG-O3-2B | #6 | J&F: 64.8J: 62.0F: 67.5 |