Text-oriented Visual Question Answering on InfoVQA
43.5ANLSHRVDA
Evaluation Results
| Method | Links | |
|---|---|---|
| HRVDAResolution=15362024.04 | 43.5 | |
| UReaderResolution=2242024.04 | 42.2 | |
| Pix2StructResolution=10242024.04 | 40 | |
| mPLUG-DocResolution=2242024.04 | 38.2 | |
| Qwen-VLResolution=448, Open-source evaluation=true2024.04 | 29.9 | |
| SeRumResolution=1280, Fine-tuning=true2024.04 | 13.5 | |
| DonutResolution=1280, Fine-tuning=true2024.04 | 11.6 |