| video-semantic-segmentation-on-vspw | PMT-L (DINOv3-L frozen, online VSS) (extra data) | #2 | mIoU: 65.7 |
| video-instance-segmentation-on-youtube-vis-validation | PMT-L (DINOv3-L frozen, online VIS) (extra data) | #4 | mask AP: 69.2 |
| video-instance-segmentation-on-youtube-vis-2021 | PMT-L (DINOv3-L frozen, online VIS) (extra data) | #5 | mask AP: 64.3 |
| video-instance-segmentation-on-ovis-validation | PMT-L (DINOv3-L frozen, online VIS) (extra data) | #7 | mask AP: 52.0 |
| video-panoptic-segmentation-on-vipseg | PMT-L (DINOv3-L frozen, online VPS) (extra data) | #8 | VPQ: 55.5 |