Bui AD, Nguyen QT, Tran TN, Nguyen VH. AN IMPROVED MULTI-VISION CONTEXTUAL ATTENTION MODEL FOR VIETNAMESE VISUAL-BASED QUESTION ANSWERING. TCKH ĐHSP TPHCM TPHCM. 2025;22(2):247-259. doi:10.54607/hcmue.js.22.2.4328(2025)