Nguyen Van Thinh, Lang TV, Van VTT. OD-VR-Cap: Image captioning based on detecting and predicting relationships between objects. J. Comput. Sci. Cybern. [Internet]. 2024 Dec. 3 [cited 2025 Apr. 13];40(4):327-46. Available from: https://vjs.ac.vn/index.php/jcc/article/view/20929