| open-world-video-segmentation-on-burst-val | DEVA (Mask2Former) | #1 | OWTA (all): 69.9OWTA (com): 75.2OWTA (unc): 41.5 |
| open-world-video-segmentation-on-burst-val | DEVA (EntitySeg) | #2 | OWTA (all): 69.5OWTA (com): 73.3OWTA (unc): 50.5 |
| referring-expression-segmentation-on-davis | DEVA (ReferFormer) | #3 | J&F 1st frame: 66.3 |
| referring-expression-segmentation-on-refer-1 | DEVA (ReferFormer) | #11 | J&F: 66.0 |
| semi-supervised-video-object-segmentation-on-1 | DEVA | #7 | J&F: 83.2Jaccard (Mean): 79.6F-measure (Mean): 86.8FPS: 25.3 |
| semi-supervised-video-object-segmentation-on-21 | DEVA (with OVIS) | #8 | J&F: 66.5J: 62.3F: 70.8FPS: 25.3 |
| semi-supervised-video-object-segmentation-on-21 | DEVA (no OVIS) | #11 | J&F: 60.0J: 55.8F: 64.3FPS: 25.3 |
| unsupervised-video-object-segmentation-on-10 | DEVA (DIS) | #2 | G: 88.9J: 87.6F: 90.2 |
| unsupervised-video-object-segmentation-on-4 | DEVA (EntitySeg) | #1 | J&F: 73.4Jaccard (Mean): 70.4F-measure (Mean): 76.4 |
| unsupervised-video-object-segmentation-on-5 | DEVA (EntitySeg) | #1 | J&F: 62.1 |
| video-panoptic-segmentation-on-vipseg | DEVA (Mask2Former - SwinB) | #6 | VPQ: 55.0STQ: 52.2 |
| visual-object-tracking-on-davis-2017 | DEVA | #8 | J&F: 87.6Jaccard (Mean): 84.2F-measure (Mean): 91.0… |