| Benchmark | Model | Rank | Results |
|---|---|---|---|
| video-instance-segmentation-on-ovis-validation | VITA (Swin-L) | #29 | mask AP: 27.7AP50: 51.9AP75: 24.9AR1: 14.9AR10: 33.0 |
| video-instance-segmentation-on-youtube-vis-2021 | VITA (Swin-L) | #11 | mask AP: 57.5AP50: 80.6AP75: 61.0AR1: 47.7AR10: 62.6 |