| semi-supervised-video-object-segmentation-on-lvos-validation | SAM2.1Long-L (extra data) | #1 | J&F: 83.4 |
| semi-supervised-video-object-segmentation-on-sa-v-test | SAM2.1Long-L (extra data) | #2 | J&F: 81.2 |
| semi-supervised-video-object-segmentation-on-sa-v-val | SAM2.1Long-L (extra data) | #2 | J&F: 81.1 |
| semi-supervised-video-object-segmentation-on-mose | SAM2.1Long-L (extra data) | #4 | J&F: 75.2 |
| visual-object-tracking-on-didi | SAM2.1Long | #4 | Tracking quality: 0.646 |
| visual-object-tracking-on-davis-2017 | SAM2.1Long-L (extra data) | #5 | J&F: 90.2 |