Which Tags Are Related to Visual Content?
Identifieur interne : 000637 ( Main/Exploration ); précédent : 000636; suivant : 000638Which Tags Are Related to Visual Content?
Auteurs : Yinghai Zhao [République populaire de Chine] ; Zheng-Jun Zha [Singapour] ; Shanshan Li [République populaire de Chine] ; Xiuqing Wu [République populaire de Chine]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2010.
Abstract
Abstract: Photo sharing services allow user to share one’s photos on the Web, as well as to annotate the photos with tags. Such web sites currently cumulate large volume of images and abundant tags. These resources have brought forth a lot of new research topics. In this paper, we propose to automatically identify which tags are related to the content of images, i.e. which tags are content-related. A data-driven method is developed to investigate the relatedness between a tag and the image visual content. We conduct extensive experiments over a dataset of 149,915 Flickr images. The experimental results demonstrate the effectiveness of our method.
Url:
DOI: 10.1007/978-3-642-11301-7_67
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002622
- to stream Istex, to step Curation: 002450
- to stream Istex, to step Checkpoint: 000217
- to stream Main, to step Merge: 000642
- to stream Main, to step Curation: 000637
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Which Tags Are Related to Visual Content?</title>
<author><name sortKey="Zhao, Yinghai" sort="Zhao, Yinghai" uniqKey="Zhao Y" first="Yinghai" last="Zhao">Yinghai Zhao</name>
</author>
<author><name sortKey="Zha, Zheng Jun" sort="Zha, Zheng Jun" uniqKey="Zha Z" first="Zheng-Jun" last="Zha">Zheng-Jun Zha</name>
</author>
<author><name sortKey="Li, Shanshan" sort="Li, Shanshan" uniqKey="Li S" first="Shanshan" last="Li">Shanshan Li</name>
</author>
<author><name sortKey="Wu, Xiuqing" sort="Wu, Xiuqing" uniqKey="Wu X" first="Xiuqing" last="Wu">Xiuqing Wu</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:C442ADE74FFB83C18B15CD46BC88F79A837EDAC1</idno>
<date when="2010" year="2010">2010</date>
<idno type="doi">10.1007/978-3-642-11301-7_67</idno>
<idno type="url">https://api.istex.fr/document/C442ADE74FFB83C18B15CD46BC88F79A837EDAC1/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002622</idno>
<idno type="wicri:Area/Istex/Curation">002450</idno>
<idno type="wicri:Area/Istex/Checkpoint">000217</idno>
<idno type="wicri:doubleKey">0302-9743:2010:Zhao Y:which:tags:are</idno>
<idno type="wicri:Area/Main/Merge">000642</idno>
<idno type="wicri:Area/Main/Curation">000637</idno>
<idno type="wicri:Area/Main/Exploration">000637</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Which Tags Are Related to Visual Content?</title>
<author><name sortKey="Zhao, Yinghai" sort="Zhao, Yinghai" uniqKey="Zhao Y" first="Yinghai" last="Zhao">Yinghai Zhao</name>
<affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>University of Science and Technology of China, 230027, Hefei, Anhui</wicri:regionArea>
<wicri:noRegion>Anhui</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country>
</affiliation>
</author>
<author><name sortKey="Zha, Zheng Jun" sort="Zha, Zheng Jun" uniqKey="Zha Z" first="Zheng-Jun" last="Zha">Zheng-Jun Zha</name>
<affiliation wicri:level="4"><country xml:lang="fr">Singapour</country>
<wicri:regionArea>National University of Singapore, 639798</wicri:regionArea>
<orgName type="university">Université nationale de Singapour</orgName>
</affiliation>
<affiliation><wicri:noCountry code="no comma">E-mail: junzzustc@gmail.com</wicri:noCountry>
</affiliation>
</author>
<author><name sortKey="Li, Shanshan" sort="Li, Shanshan" uniqKey="Li S" first="Shanshan" last="Li">Shanshan Li</name>
<affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>University of Science and Technology of China, 230027, Hefei, Anhui</wicri:regionArea>
<wicri:noRegion>Anhui</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country>
</affiliation>
</author>
<author><name sortKey="Wu, Xiuqing" sort="Wu, Xiuqing" uniqKey="Wu X" first="Xiuqing" last="Wu">Xiuqing Wu</name>
<affiliation wicri:level="1"><country xml:lang="fr">République populaire de Chine</country>
<wicri:regionArea>University of Science and Technology of China, 230027, Hefei, Anhui</wicri:regionArea>
<wicri:noRegion>Anhui</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">République populaire de Chine</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2010</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">C442ADE74FFB83C18B15CD46BC88F79A837EDAC1</idno>
<idno type="DOI">10.1007/978-3-642-11301-7_67</idno>
<idno type="ChapterID">67</idno>
<idno type="ChapterID">Chap67</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Photo sharing services allow user to share one’s photos on the Web, as well as to annotate the photos with tags. Such web sites currently cumulate large volume of images and abundant tags. These resources have brought forth a lot of new research topics. In this paper, we propose to automatically identify which tags are related to the content of images, i.e. which tags are content-related. A data-driven method is developed to investigate the relatedness between a tag and the image visual content. We conduct extensive experiments over a dataset of 149,915 Flickr images. The experimental results demonstrate the effectiveness of our method.</div>
</front>
</TEI>
<affiliations><list><country><li>République populaire de Chine</li>
<li>Singapour</li>
</country>
<orgName><li>Université nationale de Singapour</li>
</orgName>
</list>
<tree><country name="République populaire de Chine"><noRegion><name sortKey="Zhao, Yinghai" sort="Zhao, Yinghai" uniqKey="Zhao Y" first="Yinghai" last="Zhao">Yinghai Zhao</name>
</noRegion>
<name sortKey="Li, Shanshan" sort="Li, Shanshan" uniqKey="Li S" first="Shanshan" last="Li">Shanshan Li</name>
<name sortKey="Li, Shanshan" sort="Li, Shanshan" uniqKey="Li S" first="Shanshan" last="Li">Shanshan Li</name>
<name sortKey="Wu, Xiuqing" sort="Wu, Xiuqing" uniqKey="Wu X" first="Xiuqing" last="Wu">Xiuqing Wu</name>
<name sortKey="Wu, Xiuqing" sort="Wu, Xiuqing" uniqKey="Wu X" first="Xiuqing" last="Wu">Xiuqing Wu</name>
<name sortKey="Zhao, Yinghai" sort="Zhao, Yinghai" uniqKey="Zhao Y" first="Yinghai" last="Zhao">Yinghai Zhao</name>
</country>
<country name="Singapour"><noRegion><name sortKey="Zha, Zheng Jun" sort="Zha, Zheng Jun" uniqKey="Zha Z" first="Zheng-Jun" last="Zha">Zheng-Jun Zha</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000637 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000637 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:C442ADE74FFB83C18B15CD46BC88F79A837EDAC1 |texte= Which Tags Are Related to Visual Content? }}
This area was generated with Dilib version V0.6.32. |