Batra, V, He, Y and Vogiatzis, G (2018) Neural Caption Generation for News Images. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). ISSN 979-10-95546-00-9

[thumbnail of L18-1273.pdf] Text
L18-1273.pdf - Published Version
Restricted to Repository staff only

Download (928kB)


Automatic caption generation of images has gained significant interest. It gives rise to a lot of interesting image-related applications. For example, it could help in image/video retrieval and management of vast amount of multimedia data available on the Internet. It could also help in development of tools that can aid visually impaired individuals in accessing multimedia content. In this paper, we particularly focus on news images and propose a methodology for automatically generating captions for news paper articles consisting of a text paragraph and an image. We propose several deep neural network architectures built upon Recurrent Neural Networks. Results on a BBC News dataset show that our proposed approach outperforms a traditional method based on Latent Dirichlet Allocation using both automatic evaluation based on BLEU scores and human evaluation.

Item Type: Article
Additional Information: The LREC 2018 Proceedings are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. For any more information on this article, or on the conference, please visit; (page for the paper) (page for the conference)
Uncontrolled Keywords: Recurrent Neural Networks, Image caption generation, Deep learning, Order Embedding
Subjects: P Language and Literature > PE English
P Language and Literature > PN Literature (General) > PN1990 Broadcasting
Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
T Technology > TR Photography
Divisions: Faculty of Natural Sciences > School of Computing and Mathematics
Depositing User: Symplectic
Date Deposited: 28 May 2020 08:21
Last Modified: 28 May 2020 08:21

Actions (login required)

View Item
View Item