Co-author(s) :

Sarukhanyan Hakob

Abstract:

Automated caption generation for digital images is one of the fundamental problems in artificial intelligence. Most of the existing works use LSTM (Long Short-Term Memory) as a recurrent neural network cell to solve this task. After training, their deep neural models can generate an image caption. But there is an issue, the next predicted word of the caption depends mainly on the last predicted word, rather than the image content. In this paper, we present model that can automatically generate an image description and is based on a recurrent neural network with modified LSTM cell that has an additional gate responsible for image features. This modification results in generation of more accurate captions. We have trained and tested our model on MSCOCO image dataset by using only images and their captions.

Identifier:

oai:noad.sci.am:135815

Language:

English

URL:

Additional Information:

agasy18@gmail.com ; hakop@ipia.sci.am

Affiliation:

Institute for Informatics and Automation Problems

Country:

Armenia

Year:

2017

Time period:

September25-29

Conference title:

11th International Conference on Computer Science and Information Technologies CSIT 2017

Place:

Yerevan

Participation type:

oral