Multimodal AI for Image Captioning: Using VGG16 and Attention-Enhanced LSTM Networks for Visual Description Generation. TechPioneer Journal of Engineering and Sciences, [S. l.], v. 2, n. 1, p. 48–58, 2025. Disponível em: https://www.macawpublications.com/Journals/index.php/TPJES/article/view/150.. Acesso em: 19 may. 2025.