| video-instance-segmentation-on-ovis-1 | InstanceFormer (Swin-L) | #31 | mask AP: 22.8AP50: 42.5AP75: 21.61AR1: 12.9AR10: 29.3 |
| video-instance-segmentation-on-ovis-1 | InstanceFormer(ResNet-50) | #32 | mask AP: 20.0AP50: 40.7AP75: 18.1AR1: 12AR10: 27.1 |
| video-instance-segmentation-on-youtube-vis-1 | InstanceFormer(Swin-L) | #11 | mask AP: 56.3AP50: 78.0AP75: 64.2AR1: 50.9AR10: 61.6 |
| video-instance-segmentation-on-youtube-vis-1 | InstanceFormer(ResNet-50) | #19 | mask AP: 45.6AP50: 68.6AP75: 49.6AR1: 42.1AR10: 53.5 |
| video-instance-segmentation-on-youtube-vis-2 | InstanceFormer (Swin-L) | #17 | mask AP: 51.0AP50: 73.7AP75: 56.9AR1: 42.8AR10: 56.0 |
| video-instance-segmentation-on-youtube-vis-2 | InstanceFormer (ResNet-50) | #22 | mask AP: 40.8AP50: 62.4AP75: 43.7AR1: 36.1AR10: 48.1 |
| video-instance-segmentation-on-youtube-vis-3 | InstanceFormer (Swin) | #6 | mAP_L: 26.3AP50_L: 44.6AP75_L: 27.3AR1_L: 25.0AR10_L: 29.2 |
| video-instance-segmentation-on-youtube-vis-3 | InstanceFormer (Resnet-50) | #7 | mAP_L: 24.8AP50_L: 49.5AP75_L: 26.7AR1_L: 23.9AR10_L: 30.1 |