TRINS-VQA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-rich Image Question Answering (Extraction) | TRINS-VQA | Accuracy63.6 | 10 | |
| Text-rich Image Question Answering (Abstract) | TRINS-VQA (test) | B@145.3 | 10 | |
| Text-rich image question-answering | TRINS-VQA Human | Accuracy58.8 | 4 | |
| Text-rich Image Question Answering (Extraction) | TRINS-VQA (test) | Accuracy- | 0 |
Showing 4 of 4 rows