Nguyen Van Thinh, Tran Van Lang, and Van The Thanh Van. “OD-VR-Cap: Image Captioning Based on Detecting and Predicting Relationships Between Objects”. <i>Journal of Computer Science and Cybernetics</i> 40, no. 4 (December 3, 2024): 327–346. Accessed November 4, 2025. https://jcc.vast.vn/jcc/article/view/20929.