| referring-expression-segmentation-on-davis | UniVS(Swin-L) | #8 | J&F 1st frame: 59.4?J&F Full video: 59.4 |
| referring-expression-segmentation-on-refer-1 | UniVS(Swin-L) | #19 | J&F: 58.0J: 56.8F: 59.5 |
| video-instance-segmentation-on-ovis-1 | UniVS(Swin-L) | #16 | mask AP: 41.7 |
| video-instance-segmentation-on-youtube-vis-1 | UniVS(Swin-L) | #7 | mask AP: 60.0AP50: 82.1AP75: 65.3AR1: 54.7AR10: 66.8 |
| video-instance-segmentation-on-youtube-vis-2 | UniVS(Swin-L) | #10 | mask AP: 57.9AP50: 79.4AP75: 63.3AR1: 46.2AR10: 63.1 |
| video-object-segmentation-on-davis-2017-val | UniVS(Swin-L) | #3 | Mean Jaccard & F-Measure: 76.2F-measure: 79.5Jaccard: 72.8 |
| video-object-segmentation-on-youtube-vos-1 | UniVS(Swin-L) | #2 | Mean Jaccard & F-Measure: 71.5 |
| video-panoptic-segmentation-on-vipseg | UniVS(Swin-L) | #8 | VPQ: 49.3STQ: 58.2 |
| video-semantic-segmentation-on-vspw | UniVS(Swin-L) | #2 | mIoU: 59.8 |