Bui, Anh Dai, et al. “AN IMPROVED MULTI-VISION CONTEXTUAL ATTENTION MODEL FOR VIETNAMESE VISUAL-BASED QUESTION ANSWERING”. Ho Chi Minh City University of Education Journal of Science, vol. 22, no. 2, Feb. 2025, pp. 247-59, doi:10.54607/hcmue.js.22.2.4328(2025).