Kus669/ViSceT5-ViTextVQA
Visual Question Answering • 0.3B • Updated • 50
Vietnamese scene-text VQA: ViT5 + QA-ViT + Consformer + OCR, final models.
Note Final model: QA-ViT + Consformer + DOVE + OACT (ocr_both). Test EM 36.01 / F1 58.93
Note Final model. Test EM 13.21 / F1 58.76 / CIDEr 3.72