Deep Learning for Automatic Image Captioning in Poor Training Conditions

Recent advancements in Deep Learning have proved that an architecture that combines Convolutional Neural Networks and Recurrent Neural Networks enables the definition of very effective methods for the automatic captioning of images. The disadvantage that comes with this straightforward result is tha...

Full description

Saved in:
Bibliographic Details
Main Authors: Caterina Masotti, Danilo Croce, Roberto Basili
Format: Article
Language:English
Published: Accademia University Press 2018-06-01
Series:IJCoL
Online Access:https://journals.openedition.org/ijcol/538
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850109736365588480
author Caterina Masotti
Danilo Croce
Roberto Basili
author_facet Caterina Masotti
Danilo Croce
Roberto Basili
author_sort Caterina Masotti
collection DOAJ
description Recent advancements in Deep Learning have proved that an architecture that combines Convolutional Neural Networks and Recurrent Neural Networks enables the definition of very effective methods for the automatic captioning of images. The disadvantage that comes with this straightforward result is that this approach requires the existence of large-scale corpora, which are not available for many languages.This paper introduces a simple methodology to automatically acquire a large-scale corpus of 600 thousand image/sentences pairs in Italian. At the best of our knowledge, this corpus has been used to train one of the first neural captioning systems for the same language. The experimental evaluation over a subset of validated image/captions pairs suggests that the achieved results are comparable with the English counterpart, despite a reduced amount of training examples.
format Article
id doaj-art-32e280a339fc4cdc9de082d482f34c39
institution OA Journals
issn 2499-4553
language English
publishDate 2018-06-01
publisher Accademia University Press
record_format Article
series IJCoL
spelling doaj-art-32e280a339fc4cdc9de082d482f34c392025-08-20T02:37:59ZengAccademia University PressIJCoL2499-45532018-06-0141435510.4000/ijcol.538Deep Learning for Automatic Image Captioning in Poor Training ConditionsCaterina MasottiDanilo CroceRoberto BasiliRecent advancements in Deep Learning have proved that an architecture that combines Convolutional Neural Networks and Recurrent Neural Networks enables the definition of very effective methods for the automatic captioning of images. The disadvantage that comes with this straightforward result is that this approach requires the existence of large-scale corpora, which are not available for many languages.This paper introduces a simple methodology to automatically acquire a large-scale corpus of 600 thousand image/sentences pairs in Italian. At the best of our knowledge, this corpus has been used to train one of the first neural captioning systems for the same language. The experimental evaluation over a subset of validated image/captions pairs suggests that the achieved results are comparable with the English counterpart, despite a reduced amount of training examples.https://journals.openedition.org/ijcol/538
spellingShingle Caterina Masotti
Danilo Croce
Roberto Basili
Deep Learning for Automatic Image Captioning in Poor Training Conditions
IJCoL
title Deep Learning for Automatic Image Captioning in Poor Training Conditions
title_full Deep Learning for Automatic Image Captioning in Poor Training Conditions
title_fullStr Deep Learning for Automatic Image Captioning in Poor Training Conditions
title_full_unstemmed Deep Learning for Automatic Image Captioning in Poor Training Conditions
title_short Deep Learning for Automatic Image Captioning in Poor Training Conditions
title_sort deep learning for automatic image captioning in poor training conditions
url https://journals.openedition.org/ijcol/538
work_keys_str_mv AT caterinamasotti deeplearningforautomaticimagecaptioninginpoortrainingconditions
AT danilocroce deeplearningforautomaticimagecaptioninginpoortrainingconditions
AT robertobasili deeplearningforautomaticimagecaptioninginpoortrainingconditions