A Deep Learning Approach to Automatic Caption Generation for News Images

Vishwash Batra, Yulan He, George Vogiatzis

Research output: Chapter in Book/Published conference outputConference publication

Abstract

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.
Original languageEnglish
Title of host publicationThe 11th International Conference on Language Resources and Evaluation (LREC)
Publication statusPublished - 1 Jan 2019
EventThe 11th International Conference on Language Resources and Evaluation (LREC) - Miyazaki, Japan
Duration: 7 May 201812 May 2018
http://lrec2018.lrec-conf.org/en/

Conference

ConferenceThe 11th International Conference on Language Resources and Evaluation (LREC)
Country/TerritoryJapan
CityMiyazaki
Period7/05/1812/05/18
Internet address

Bibliographical note

The LREC 2018 Proceedings are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Keywords

  • Recurrent Neural Networks
  • Image caption generation
  • Deep learning
  • Order Embedding

Fingerprint

Dive into the research topics of 'A Deep Learning Approach to Automatic Caption Generation for News Images'. Together they form a unique fingerprint.

Cite this