Multi-modal Solution for Unconstrained News Story Retrieval
Identifieur interne : 000282 ( Main/Exploration ); précédent : 000281; suivant : 000283Multi-modal Solution for Unconstrained News Story Retrieval
Auteurs : Ehsan Younessian [Singapour] ; Deepu Rajan [Singapour]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2012.
Abstract
Abstract: We propose a multi-modal approach to retrieve associated news stories sharing the same main topic. In the textual domain, we utilize Automatic Speech Recognition (ASR) and refined Optical Character Recognition (OCR) transcripts while in the visual domain we employ a Near Duplicate Keyframe detection method to identify stories with common visual clues. In addition, we adopt another visual representation namely semantic signature, indicating pre-defined semantic concepts included in the news story, to improve the discriminativness of visual modality. We propose a query-class weighting scheme to integrate the retrieval outcomes gained from visual modalities. Experimental results show the distinguishing power of the enhanced representation in individual modalities and the superiority of our fusion approach performance compared to existing strategies.
Url:
DOI: 10.1007/978-3-642-27355-1_19
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000059
- to stream Istex, to step Curation: 000058
- to stream Istex, to step Checkpoint: 000017
- to stream Main, to step Merge: 000285
- to stream Main, to step Curation: 000282
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Multi-modal Solution for Unconstrained News Story Retrieval</title><author><name sortKey="Younessian, Ehsan" sort="Younessian, Ehsan" uniqKey="Younessian E" first="Ehsan" last="Younessian">Ehsan Younessian</name></author><author><name sortKey="Rajan, Deepu" sort="Rajan, Deepu" uniqKey="Rajan D" first="Deepu" last="Rajan">Deepu Rajan</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:4833BF1D0720B0E6B29B11F47C14CBF59039A126</idno><date when="2012" year="2012">2012</date><idno type="doi">10.1007/978-3-642-27355-1_19</idno><idno type="url">https://api.istex.fr/document/4833BF1D0720B0E6B29B11F47C14CBF59039A126/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000059</idno><idno type="wicri:Area/Istex/Curation">000058</idno><idno type="wicri:Area/Istex/Checkpoint">000017</idno><idno type="wicri:doubleKey">0302-9743:2012:Younessian E:multi:modal:solution</idno><idno type="wicri:Area/Main/Merge">000285</idno><idno type="wicri:Area/Main/Curation">000282</idno><idno type="wicri:Area/Main/Exploration">000282</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Multi-modal Solution for Unconstrained News Story Retrieval</title><author><name sortKey="Younessian, Ehsan" sort="Younessian, Ehsan" uniqKey="Younessian E" first="Ehsan" last="Younessian">Ehsan Younessian</name><affiliation wicri:level="1"><country xml:lang="fr">Singapour</country><wicri:regionArea>School of Computer Engineering, Nanyang Technological University</wicri:regionArea><wicri:noRegion>Nanyang Technological University</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Singapour</country></affiliation></author><author><name sortKey="Rajan, Deepu" sort="Rajan, Deepu" uniqKey="Rajan D" first="Deepu" last="Rajan">Deepu Rajan</name><affiliation wicri:level="1"><country xml:lang="fr">Singapour</country><wicri:regionArea>School of Computer Engineering, Nanyang Technological University</wicri:regionArea><wicri:noRegion>Nanyang Technological University</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Singapour</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2012</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">4833BF1D0720B0E6B29B11F47C14CBF59039A126</idno><idno type="DOI">10.1007/978-3-642-27355-1_19</idno><idno type="ChapterID">19</idno><idno type="ChapterID">Chap19</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: We propose a multi-modal approach to retrieve associated news stories sharing the same main topic. In the textual domain, we utilize Automatic Speech Recognition (ASR) and refined Optical Character Recognition (OCR) transcripts while in the visual domain we employ a Near Duplicate Keyframe detection method to identify stories with common visual clues. In addition, we adopt another visual representation namely semantic signature, indicating pre-defined semantic concepts included in the news story, to improve the discriminativness of visual modality. We propose a query-class weighting scheme to integrate the retrieval outcomes gained from visual modalities. Experimental results show the distinguishing power of the enhanced representation in individual modalities and the superiority of our fusion approach performance compared to existing strategies.</div></front></TEI><affiliations><list><country><li>Singapour</li></country></list><tree><country name="Singapour"><noRegion><name sortKey="Younessian, Ehsan" sort="Younessian, Ehsan" uniqKey="Younessian E" first="Ehsan" last="Younessian">Ehsan Younessian</name></noRegion><name sortKey="Rajan, Deepu" sort="Rajan, Deepu" uniqKey="Rajan D" first="Deepu" last="Rajan">Deepu Rajan</name><name sortKey="Rajan, Deepu" sort="Rajan, Deepu" uniqKey="Rajan D" first="Deepu" last="Rajan">Deepu Rajan</name><name sortKey="Younessian, Ehsan" sort="Younessian, Ehsan" uniqKey="Younessian E" first="Ehsan" last="Younessian">Ehsan Younessian</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 000282 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000282 | 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:4833BF1D0720B0E6B29B11F47C14CBF59039A126
|texte= Multi-modal Solution for Unconstrained News Story Retrieval
}}
| This area was generated with Dilib version V0.6.32. |  |