Multimodal AI for Image Captioning: Using VGG16 and Attention-Enhanced LSTM Networks for Visual Description Generation. TPJ Eng. Sci. [Internet]. 2025 Apr. 30 [cited 2025 May 19];2(1):48-5. Available from: https://www.macawpublications.com/Journals/index.php/TPJES/article/view/150