| referring-expression-segmentation-on-a2d | SOC (Video-Swin-B) | #2 | AP: 0.573IoU overall: 0.807IoU mean: 0.725Precision@0.5: 0.851… |
| referring-expression-segmentation-on-a2d | SOC (Video-Swin-T) | #4 | AP: 0.504IoU overall: 0.747IoU mean: 0.669Precision@0.5: 0.79… |
| referring-expression-segmentation-on-j-hmdb | SOC (Video-Swin-B) | #2 | AP: 0.446IoU overall: 0.736IoU mean: 0.723Precision@0.5: 0.969… |
| referring-expression-segmentation-on-j-hmdb | SOC (Video-Swin-T) | #3 | AP: 0.397IoU overall: 0.707IoU mean: 0.701Precision@0.5: 0.947… |
| referring-expression-segmentation-on-refer-1 | SOC (Joint training, Video-Swin-B) | #6 | J&F: 67.3±0.5J: 65.3F: 69.3 |
| referring-expression-segmentation-on-refer-1 | SOC (Video-Swin-T) | #18 | J&F: 59.2J: 57.8F: 60.5 |
| referring-video-object-segmentation-on-long | SOC | #4 | J&F: 34.9tIoU: 68.1vIoU: 28.6 |
| referring-video-object-segmentation-on-ref | SOC | #4 | J&F: 65.8J: 62.5F: 69.1 |
| referring-video-object-segmentation-on-refer | SOC | #6 | J&F: 66.0J: 64.1F: 67.9 |