TRUONG, Xuan Linh. Integrating features and harnessing pre-trained visual-language models for enhancing VQA reading comprehension. <b>Journal of Computer Science and Cybernetics</b>, <i>[S. l.]</i>, v. 41, n. 3, p. 323–336, 2025. DOI: 10.15625/1813-9663/20525. Disponível em: https://jcc.vast.vn/jcc/article/view/20525. Acesso em: 11 jan. 2026.