Journal of Engineering and Applied Sciences
ISSN: Online 1818-7803ISSN: Print 1816-949x
Abstract
Modern development in visualization-to-verbal communication troubles have been attained through a combination of deep neural networks and Recurrent Neural Networks (RNNs). This mechanism is employed to combine in exterior skill which is seriously significant to answer advanced visual questions. A visual question answering model is calculated which merge an interior depiction of the subject matter of an picture with data obtained from a common skill foundation to respond a wide point of picture-based queries. It especially, permits questions to be raised where the picture only does not have the data necessary to pick the suitable respond.
How to cite this article:
Maram Adil Ali Alaziz and Suhaam Adnan Abdul Kareem. A Novel Method for Image Captioning Based on Attributes and External Knowledge.
DOI: https://doi.org/10.36478/jeasci.2019.610.614
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2019.610.614