| video-instance-segmentation-on-ovis-1 | TarViS (Swin-L) | #12 | mask AP: 43.2AP50: 67.8AP75: 44.6AR1: 18.0AR10: 50.4 |
| video-instance-segmentation-on-ovis-1 | TarViS (Swin-T) | #24 | mask AP: 34.0AP50: 55.0AP75: 34.4AR1: 16.1AR10: 40.9 |
| video-instance-segmentation-on-ovis-1 | TarViS (ResNet-50) | #26 | mask AP: 31.1AP50: 52.5AP75: 30.4AR1: 15.9AR10: 39.9 |
| video-instance-segmentation-on-youtube-vis-2 | TarViS (Swin-L) | #6 | mask AP: 60.2AP50: 81.4AP75: 67.6AR1: 47.6AR10: 64.8 |
| video-instance-segmentation-on-youtube-vis-2 | TarViS (Swin-T) | #18 | mask AP: 50.9AP50: 71.6AP75: 56.6AR1: 42.2AR10: 57.2 |
| video-instance-segmentation-on-youtube-vis-2 | TarViS (ResNet-50) | #20 | mask AP: 48.3AP50: 69.6AP75: 53.2AR1: 40.5AR10: 55.9 |
| video-panoptic-segmentation-on-cityscapes-vps | TarViS (Swin-L) | #4 | VPQ: 58.9VPQ (thing): 43.7VPQ (stuff): 69.9 |
| video-panoptic-segmentation-on-cityscapes-vps | TarViS (Swin-T) | #5 | VPQ: 58.0VPQ (thing): 42.9VPQ (stuff): 69.0 |
| video-panoptic-segmentation-on-cityscapes-vps | TarViS (ResNet-50) | #7 | VPQ: 53.3VPQ (thing): 35.9VPQ (stuff): 66.0 |
| video-panoptic-segmentation-on-kitti-step | TarViS (Swin-L) | #2 | AQ: 72.0SQ: 72.0STQ: 73.0 |
| video-panoptic-segmentation-on-kitti-step | TarViS (Swin-T) | #3 | AQ: 71.2SQ: 69.9STQ: 70.6 |
| video-panoptic-segmentation-on-kitti-step | TarViS (ResNet-50) | #4 | AQ: 70.3SQ: 68.8STQ: 69.6 |
| video-panoptic-segmentation-on-vipseg | TarViS (Swin-L) | #9 | VPQ: 48.0STQ: 52.9 |
| video-panoptic-segmentation-on-vipseg | TarViS (Swin-T) | #11 | VPQ: 35.8STQ: 45.3 |
| video-panoptic-segmentation-on-vipseg | TarViS (ResNet-50) | #12 | VPQ: 33.5STQ: 43.1 |
| visual-object-tracking-on-davis-2017 | TarViS | #19 | J&F: 85.3Jaccard (Mean): 81.7F-measure (Mean): 88.5 |