| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Question Answering | This-Is-My-Img Single-Concept | VQA Accuracy84.2 | 4 | |
| Visual Question Answering | This-Is-My-Img Multi-Concept | Accuracy63.6 | 4 | |
| Visual Recognition | This-Is-My-Img Single-concept (test) | Precision90.1 | 3 | |
| Visual Recognition | This-Is-My-Img Multi-concept | Precision96.1 | 2 |