| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Fine-Grained Open-Vocabulary Object Detection | FG-OVD | AP (Hard)66.1 | 20 | |
| Fine-grained Open-vocabulary Object Detection | FG-OVD 1.0 (test) | Score (Hard)57.5 | 17 | |
| Fine-Grained Retrieval | FG-OVD Easy | R@168.7 | 9 | |
| Fine-Grained Retrieval | FG-OVD (Medium) | R@166.6 | 9 | |
| Fine-Grained Retrieval | FG-OVD Hard split | R@146.1 | 9 | |
| Fine-Grained Retrieval | FG-OVD (Trivial split) | R@183.4 | 8 | |
| Fine-grained Image-Text Alignment | FG-OVD | Accuracy (Hard)19.24 | 5 | |
| Object Detection | FG-OVD standard (test) | AP66.4 | 4 |