Comparison of Feature Sets Using Multimedia Translation
Identifieur interne : 001734 ( Main/Exploration ); précédent : 001733; suivant : 001735Comparison of Feature Sets Using Multimedia Translation
Auteurs : P Nar Duygulu [États-Unis] ; Can Özcanl [Turquie] ; Norman Papernick [États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2003.
Abstract
Abstract: Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared using the translation model of object recognition which is motivated by the availablity of large annotated data sets. Image regions are linked to words using a model which is inspired by machine translation. Word prediction performance is used to evaluate large numbers of images.
Url:
DOI: 10.1007/978-3-540-39737-3_64
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002582
- to stream Istex, to step Curation: 002414
- to stream Istex, to step Checkpoint: 000F07
- to stream Main, to step Merge: 001811
- to stream Main, to step Curation: 001734
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Comparison of Feature Sets Using Multimedia Translation</title>
<author><name sortKey="Duygulu, P Nar" sort="Duygulu, P Nar" uniqKey="Duygulu P" first="P Nar" last="Duygulu">P Nar Duygulu</name>
</author>
<author><name sortKey="Ozcanl, Can" sort="Ozcanl, Can" uniqKey="Ozcanl C" first="Can" last="Özcanl">Can Özcanl</name>
</author>
<author><name sortKey="Papernick, Norman" sort="Papernick, Norman" uniqKey="Papernick N" first="Norman" last="Papernick">Norman Papernick</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:1016D06A07B18A6F5B9BEBB8FD44ED2254109E69</idno>
<date when="2003" year="2003">2003</date>
<idno type="doi">10.1007/978-3-540-39737-3_64</idno>
<idno type="url">https://api.istex.fr/document/1016D06A07B18A6F5B9BEBB8FD44ED2254109E69/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002582</idno>
<idno type="wicri:Area/Istex/Curation">002414</idno>
<idno type="wicri:Area/Istex/Checkpoint">000F07</idno>
<idno type="wicri:doubleKey">0302-9743:2003:Duygulu P:comparison:of:feature</idno>
<idno type="wicri:Area/Main/Merge">001811</idno>
<idno type="wicri:Area/Main/Curation">001734</idno>
<idno type="wicri:Area/Main/Exploration">001734</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Comparison of Feature Sets Using Multimedia Translation</title>
<author><name sortKey="Duygulu, P Nar" sort="Duygulu, P Nar" uniqKey="Duygulu P" first="P Nar" last="Duygulu">P Nar Duygulu</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>School of Computer Science, Carnegie Mellon University, Informedia Project, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Ozcanl, Can" sort="Ozcanl, Can" uniqKey="Ozcanl C" first="Can" last="Özcanl">Can Özcanl</name>
<affiliation wicri:level="1"><country xml:lang="fr">Turquie</country>
<wicri:regionArea>Dept of Computer Engineering, Middle East Technical University, Ankara</wicri:regionArea>
<wicri:noRegion>Ankara</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Turquie</country>
</affiliation>
</author>
<author><name sortKey="Papernick, Norman" sort="Papernick, Norman" uniqKey="Papernick N" first="Norman" last="Papernick">Norman Papernick</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>School of Computer Science, Carnegie Mellon University, Informedia Project, Pittsburgh, PA</wicri:regionArea>
<placeName><region type="state">Pennsylvanie</region>
<settlement type="city">Pittsburgh</settlement>
</placeName>
<orgName type="university">Université Carnegie-Mellon</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2003</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">1016D06A07B18A6F5B9BEBB8FD44ED2254109E69</idno>
<idno type="DOI">10.1007/978-3-540-39737-3_64</idno>
<idno type="ChapterID">64</idno>
<idno type="ChapterID">Chap64</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: Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared using the translation model of object recognition which is motivated by the availablity of large annotated data sets. Image regions are linked to words using a model which is inspired by machine translation. Word prediction performance is used to evaluate large numbers of images.</div>
</front>
</TEI>
<affiliations><list><country><li>Turquie</li>
<li>États-Unis</li>
</country>
<region><li>Pennsylvanie</li>
</region>
<settlement><li>Pittsburgh</li>
</settlement>
<orgName><li>Université Carnegie-Mellon</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Pennsylvanie"><name sortKey="Duygulu, P Nar" sort="Duygulu, P Nar" uniqKey="Duygulu P" first="P Nar" last="Duygulu">P Nar Duygulu</name>
</region>
<name sortKey="Duygulu, P Nar" sort="Duygulu, P Nar" uniqKey="Duygulu P" first="P Nar" last="Duygulu">P Nar Duygulu</name>
<name sortKey="Papernick, Norman" sort="Papernick, Norman" uniqKey="Papernick N" first="Norman" last="Papernick">Norman Papernick</name>
<name sortKey="Papernick, Norman" sort="Papernick, Norman" uniqKey="Papernick N" first="Norman" last="Papernick">Norman Papernick</name>
</country>
<country name="Turquie"><noRegion><name sortKey="Ozcanl, Can" sort="Ozcanl, Can" uniqKey="Ozcanl C" first="Can" last="Özcanl">Can Özcanl</name>
</noRegion>
<name sortKey="Ozcanl, Can" sort="Ozcanl, Can" uniqKey="Ozcanl C" first="Can" last="Özcanl">Can Özcanl</name>
</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 001734 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001734 | 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:1016D06A07B18A6F5B9BEBB8FD44ED2254109E69 |texte= Comparison of Feature Sets Using Multimedia Translation }}
This area was generated with Dilib version V0.6.32. |