Annotating News Video with Locations
Identifieur interne : 001113 ( Main/Exploration ); précédent : 001112; suivant : 001114Annotating News Video with Locations
Auteurs : Jun Yang [États-Unis] ; G. Hauptmann [États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2006.
Abstract
Abstract: The location of video scenes is an important semantic descriptor especially for broadcast news video. In this paper, we propose a learning-based approach to annotate shots of news video with locations extracted from video transcript, based on features from multiple video modalities including syntactic structure of transcript sentences, speaker identity, temporal video structure, and so on. Machine learning algorithms are adopted to combine multi-modal features to solve two sub-problems: (1) whether the location of a video shot is mentioned in the transcript, and if so, (2) among many locations in the transcript, which are correct one(s) for this shot. Experiments on TRECVID dataset demonstrate that our approach achieves approximately 85% accuracy in correctly labeling the location of any shot in news video.
Url:
DOI: 10.1007/11788034_16
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000A43
- to stream Istex, to step Curation: 000A31
- to stream Istex, to step Checkpoint: 000A86
- to stream Main, to step Merge: 001130
- to stream Main, to step Curation: 001113
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Annotating News Video with Locations</title><author><name sortKey="Yang, Jun" sort="Yang, Jun" uniqKey="Yang J" first="Jun" last="Yang">Jun Yang</name></author><author><name sortKey="Hauptmann, G" sort="Hauptmann, G" uniqKey="Hauptmann G" first="G." last="Hauptmann">G. Hauptmann</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:77A5C13580350959F2D042E5E5E909FEF27860F6</idno><date when="2006" year="2006">2006</date><idno type="doi">10.1007/11788034_16</idno><idno type="url">https://api.istex.fr/document/77A5C13580350959F2D042E5E5E909FEF27860F6/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000A43</idno><idno type="wicri:Area/Istex/Curation">000A31</idno><idno type="wicri:Area/Istex/Checkpoint">000A86</idno><idno type="wicri:doubleKey">0302-9743:2006:Yang J:annotating:news:video</idno><idno type="wicri:Area/Main/Merge">001130</idno><idno type="wicri:Area/Main/Curation">001113</idno><idno type="wicri:Area/Main/Exploration">001113</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Annotating News Video with Locations</title><author><name sortKey="Yang, Jun" sort="Yang, Jun" uniqKey="Yang J" first="Jun" last="Yang">Jun Yang</name><affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country><wicri:regionArea>School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave., 15213, 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="Hauptmann, G" sort="Hauptmann, G" uniqKey="Hauptmann G" first="G." last="Hauptmann">G. Hauptmann</name><affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country><wicri:regionArea>School of Computer Science, Carnegie Mellon University, 5000 Forbes Ave., 15213, 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>2006</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">77A5C13580350959F2D042E5E5E909FEF27860F6</idno><idno type="DOI">10.1007/11788034_16</idno><idno type="ChapterID">16</idno><idno type="ChapterID">Chap16</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: The location of video scenes is an important semantic descriptor especially for broadcast news video. In this paper, we propose a learning-based approach to annotate shots of news video with locations extracted from video transcript, based on features from multiple video modalities including syntactic structure of transcript sentences, speaker identity, temporal video structure, and so on. Machine learning algorithms are adopted to combine multi-modal features to solve two sub-problems: (1) whether the location of a video shot is mentioned in the transcript, and if so, (2) among many locations in the transcript, which are correct one(s) for this shot. Experiments on TRECVID dataset demonstrate that our approach achieves approximately 85% accuracy in correctly labeling the location of any shot in news video.</div></front></TEI><affiliations><list><country><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="Yang, Jun" sort="Yang, Jun" uniqKey="Yang J" first="Jun" last="Yang">Jun Yang</name></region><name sortKey="Hauptmann, G" sort="Hauptmann, G" uniqKey="Hauptmann G" first="G." last="Hauptmann">G. Hauptmann</name><name sortKey="Hauptmann, G" sort="Hauptmann, G" uniqKey="Hauptmann G" first="G." last="Hauptmann">G. Hauptmann</name><name sortKey="Yang, Jun" sort="Yang, Jun" uniqKey="Yang J" first="Jun" last="Yang">Jun Yang</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 001113 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001113 | 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:77A5C13580350959F2D042E5E5E909FEF27860F6
|texte= Annotating News Video with Locations
}}
| This area was generated with Dilib version V0.6.32. |  |