@inproceedings{koeva-etal-2022-multilingual,
title = "Multilingual Image Corpus {--} Towards a Multimodal and Multilingual Dataset",
author = "Koeva, Svetla and
Stoyanova, Ivelina and
Kralev, Jordan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.162",
pages = "1509--1518",
abstract = "One of the processing tasks for large multimodal data streams is automatic image description (image classification, object segmentation and classification). Although the number and the diversity of image datasets is constantly expanding, still there is a huge demand for more datasets in terms of variety of domains and object classes covered. The goal of the project Multilingual Image Corpus (MIC 21) is to provide a large image dataset with annotated objects and object descriptions in 24 languages. The Multilingual Image Corpus consists of an Ontology of visual objects (based on WordNet) and a collection of thematically related images whose objects are annotated with segmentation masks and labels describing the ontology classes. The dataset is designed both for image classification and object detection and for semantic segmentation. The main contributions of our work are: a) the provision of large collection of high quality copyright-free images; b) the formulation of the Ontology of visual objects based on WordNet noun hierarchies; c) the precise manual correction of automatic object segmentation within the images and the annotation of object classes; and d) the association of objects and images with extended multilingual descriptions based on WordNet inner- and interlingual relations. The dataset can be used also for multilingual image caption generation, image-to-text alignment and automatic question answering for images and videos.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koeva-etal-2022-multilingual">
<titleInfo>
<title>Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Koeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Stoyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Kralev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the processing tasks for large multimodal data streams is automatic image description (image classification, object segmentation and classification). Although the number and the diversity of image datasets is constantly expanding, still there is a huge demand for more datasets in terms of variety of domains and object classes covered. The goal of the project Multilingual Image Corpus (MIC 21) is to provide a large image dataset with annotated objects and object descriptions in 24 languages. The Multilingual Image Corpus consists of an Ontology of visual objects (based on WordNet) and a collection of thematically related images whose objects are annotated with segmentation masks and labels describing the ontology classes. The dataset is designed both for image classification and object detection and for semantic segmentation. The main contributions of our work are: a) the provision of large collection of high quality copyright-free images; b) the formulation of the Ontology of visual objects based on WordNet noun hierarchies; c) the precise manual correction of automatic object segmentation within the images and the annotation of object classes; and d) the association of objects and images with extended multilingual descriptions based on WordNet inner- and interlingual relations. The dataset can be used also for multilingual image caption generation, image-to-text alignment and automatic question answering for images and videos.</abstract>
<identifier type="citekey">koeva-etal-2022-multilingual</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.162</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1509</start>
<end>1518</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset
%A Koeva, Svetla
%A Stoyanova, Ivelina
%A Kralev, Jordan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F koeva-etal-2022-multilingual
%X One of the processing tasks for large multimodal data streams is automatic image description (image classification, object segmentation and classification). Although the number and the diversity of image datasets is constantly expanding, still there is a huge demand for more datasets in terms of variety of domains and object classes covered. The goal of the project Multilingual Image Corpus (MIC 21) is to provide a large image dataset with annotated objects and object descriptions in 24 languages. The Multilingual Image Corpus consists of an Ontology of visual objects (based on WordNet) and a collection of thematically related images whose objects are annotated with segmentation masks and labels describing the ontology classes. The dataset is designed both for image classification and object detection and for semantic segmentation. The main contributions of our work are: a) the provision of large collection of high quality copyright-free images; b) the formulation of the Ontology of visual objects based on WordNet noun hierarchies; c) the precise manual correction of automatic object segmentation within the images and the annotation of object classes; and d) the association of objects and images with extended multilingual descriptions based on WordNet inner- and interlingual relations. The dataset can be used also for multilingual image caption generation, image-to-text alignment and automatic question answering for images and videos.
%U https://aclanthology.org/2022.lrec-1.162
%P 1509-1518
Markdown (Informal)
[Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset](https://aclanthology.org/2022.lrec-1.162) (Koeva et al., LREC 2022)
ACL