Variational Autoencoder-Based Multiple Image Captioning Using a Caption Attention Map

Image captioning is a promising research topic that is applicable to services that search for desired content in a large amount of video data and a situation explanation service for visually impaired people. Previous research on image captioning has been focused on generating one caption per image....

Full description

Bibliographic Details

Published in:	Applied Sciences
Main Authors:	Boeun Kim, Saim Shin, Hyedong Jung
Format:	Article
Language:	English
Published:	MDPI AG 2019-07-01
Subjects:	image captioning multiple image captioning visual attention caption attention map variational autoencoder
Online Access:	https://www.mdpi.com/2076-3417/9/13/2699