Robust scene text understanding with OCR token and word alignment for Text-VQA and text-caption

Open Webpage

Zan-Xia Jin, Pinle Qin, Suzhen Lin, Jia Qin, Shuangjiao Zhai, Jianchao Zeng, Xu-Cheng Yin

Published: 2026, Last Modified: 28 Feb 2026Pattern Recognit. 2026EveryoneRevisionsBibTeXCC BY-SA 4.0