Large scale datasets for Image and Video Captioning in Italian

The application of Attention-based Deep Neural architectures to the automatic captioning of images and videos is enabling the development of increasingly performing systems. Unfortunately, while image processing is language independent, this does not hold for caption generation. Training such archit...

Full description

Saved in:
Bibliographic Details
Main Authors: Scaiella Antonio, Danilo Croce, Roberto Basili
Format: Article
Language:English
Published: Accademia University Press 2019-12-01
Series:IJCoL
Online Access:https://journals.openedition.org/ijcol/478
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850165680209395712
author Scaiella Antonio
Danilo Croce
Roberto Basili
author_facet Scaiella Antonio
Danilo Croce
Roberto Basili
author_sort Scaiella Antonio
collection DOAJ
description The application of Attention-based Deep Neural architectures to the automatic captioning of images and videos is enabling the development of increasingly performing systems. Unfortunately, while image processing is language independent, this does not hold for caption generation. Training such architectures requires the availability of (possibly large-scale) language specific resources, which are not available for many languages, such as Italian.In this paper, we present MSCOCO-it e MSR-VTT-it, two large-scale resources for image and video captioning. They have been derived by applying automatic machine translation to existing resources. Even though this approach is naive and exposed to the gathering of noisy information (depending on the quality of the automatic translator), we experimentally show that robust deep learning is enabled, rather tolerant with respect to such noise. In particular, we improve the state-of-the-art results with respect to image captioning in Italian. Moreover, in the paper we discuss the training of a system that, at the best of our knowledge, is the first video captioning system in Italian.
format Article
id doaj-art-fcaeeb6f334643b79730cbdd486105bb
institution OA Journals
issn 2499-4553
language English
publishDate 2019-12-01
publisher Accademia University Press
record_format Article
series IJCoL
spelling doaj-art-fcaeeb6f334643b79730cbdd486105bb2025-08-20T02:21:41ZengAccademia University PressIJCoL2499-45532019-12-0152496010.4000/ijcol.478Large scale datasets for Image and Video Captioning in ItalianScaiella AntonioDanilo CroceRoberto BasiliThe application of Attention-based Deep Neural architectures to the automatic captioning of images and videos is enabling the development of increasingly performing systems. Unfortunately, while image processing is language independent, this does not hold for caption generation. Training such architectures requires the availability of (possibly large-scale) language specific resources, which are not available for many languages, such as Italian.In this paper, we present MSCOCO-it e MSR-VTT-it, two large-scale resources for image and video captioning. They have been derived by applying automatic machine translation to existing resources. Even though this approach is naive and exposed to the gathering of noisy information (depending on the quality of the automatic translator), we experimentally show that robust deep learning is enabled, rather tolerant with respect to such noise. In particular, we improve the state-of-the-art results with respect to image captioning in Italian. Moreover, in the paper we discuss the training of a system that, at the best of our knowledge, is the first video captioning system in Italian.https://journals.openedition.org/ijcol/478
spellingShingle Scaiella Antonio
Danilo Croce
Roberto Basili
Large scale datasets for Image and Video Captioning in Italian
IJCoL
title Large scale datasets for Image and Video Captioning in Italian
title_full Large scale datasets for Image and Video Captioning in Italian
title_fullStr Large scale datasets for Image and Video Captioning in Italian
title_full_unstemmed Large scale datasets for Image and Video Captioning in Italian
title_short Large scale datasets for Image and Video Captioning in Italian
title_sort large scale datasets for image and video captioning in italian
url https://journals.openedition.org/ijcol/478
work_keys_str_mv AT scaiellaantonio largescaledatasetsforimageandvideocaptioninginitalian
AT danilocroce largescaledatasetsforimageandvideocaptioninginitalian
AT robertobasili largescaledatasetsforimageandvideocaptioninginitalian