NGUYEN VAN THINH; LANG, Tran Van; VAN, Van The Thanh. OD-VR-Cap: Image captioning based on detecting and predicting relationships between objects. <b>Journal of Computer Science and Cybernetics</b>, <i>[S. l.]</i>, v. 40, n. 4, p. 327–346, 2024. DOI: 10.15625/1813-9663/20929. Disponível em: https://jcc.vast.vn/jcc/article/view/20929. Acesso em: 3 nov. 2025.