| Benchmark | Model | Rank | Results |
|---|---|---|---|
| referring-expression-segmentation-on-a2d-sentences | TQF | – | AP: 0.613IoU overall: 0.824IoU mean: 0.733 |
| referring-video-object-segmentation-on-mevis | TQF-B | – | J&F: 52.8J: 49.4F: 56.1 |
| referring-video-object-segmentation-on-mevis | TQF-T | – | J&F: 50.1J: 46.8F: 53.3 |