| video-instance-segmentation-on-ovis-1 | Tube-Link(ResNet-50) | #28 | mask AP: 29.5AP50: 51.5AP75: 30.2AR1: 15.5AR10: 34.5 |
| video-instance-segmentation-on-youtube-vis-1 | Tube-Link | #4 | mask AP: 64.6AP50: 86.6AP75: 71.3AR1: 55.9AR10: 69.1 |
| video-instance-segmentation-on-youtube-vis-2 | Tube-Link(Swin-L) | #9 | mask AP: 58.4AP50: 79.4AP75: 64.3AR1: 47.5AR10: 63.6 |
| video-panoptic-segmentation-on-kitti-step | Tube-Link(Swin-base) | #5 | AQ: 69.0SQ: 74.0STQ: 72.0 |
| video-panoptic-segmentation-on-vipseg | Tube-Link(Swin-base) | #7 | VPQ: 50.4STQ: 49.4 |
| video-semantic-segmentation-on-vspw | Tube-Link(Swin-large) | #3 | mIoU: 59.6 |