Detecting Semantic Concepts from Video Using Temporal Gradients and Audio Classification
Identifieur interne : 001728 ( Main/Exploration ); précédent : 001727; suivant : 001729Detecting Semantic Concepts from Video Using Temporal Gradients and Audio Classification
Auteurs : Mika Rautiainen [Finlande] ; Tapio Sepp Nen [Finlande] ; Jani Penttil [Finlande] ; Johannes Peltola [Finlande]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2003.
Abstract
Abstract: In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.
Url:
DOI: 10.1007/3-540-45113-7_26
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001158
- to stream Istex, to step Curation: 001103
- to stream Istex, to step Checkpoint: 000F01
- to stream Main, to step Merge: 001805
- to stream Main, to step Curation: 001728
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Detecting Semantic Concepts from Video Using Temporal Gradients and Audio Classification</title><author><name sortKey="Rautiainen, Mika" sort="Rautiainen, Mika" uniqKey="Rautiainen M" first="Mika" last="Rautiainen">Mika Rautiainen</name></author><author><name sortKey="Sepp Nen, Tapio" sort="Sepp Nen, Tapio" uniqKey="Sepp Nen T" first="Tapio" last="Sepp Nen">Tapio Sepp Nen</name></author><author><name sortKey="Penttil, Jani" sort="Penttil, Jani" uniqKey="Penttil J" first="Jani" last="Penttil">Jani Penttil</name></author><author><name sortKey="Peltola, Johannes" sort="Peltola, Johannes" uniqKey="Peltola J" first="Johannes" last="Peltola">Johannes Peltola</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:0B6CD3EE5AB28BFF813BE4D282217527E35EDD21</idno><date when="2003" year="2003">2003</date><idno type="doi">10.1007/3-540-45113-7_26</idno><idno type="url">https://api.istex.fr/document/0B6CD3EE5AB28BFF813BE4D282217527E35EDD21/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001158</idno><idno type="wicri:Area/Istex/Curation">001103</idno><idno type="wicri:Area/Istex/Checkpoint">000F01</idno><idno type="wicri:doubleKey">0302-9743:2003:Rautiainen M:detecting:semantic:concepts</idno><idno type="wicri:Area/Main/Merge">001805</idno><idno type="wicri:Area/Main/Curation">001728</idno><idno type="wicri:Area/Main/Exploration">001728</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Detecting Semantic Concepts from Video Using Temporal Gradients and Audio Classification</title><author><name sortKey="Rautiainen, Mika" sort="Rautiainen, Mika" uniqKey="Rautiainen M" first="Mika" last="Rautiainen">Mika Rautiainen</name><affiliation wicri:level="1"><country xml:lang="fr">Finlande</country><wicri:regionArea>MediaTeam Oulu, University of Oulu, P.O.BOX 4500, FIN-90014</wicri:regionArea><wicri:noRegion>FIN-90014</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Finlande</country></affiliation></author><author><name sortKey="Sepp Nen, Tapio" sort="Sepp Nen, Tapio" uniqKey="Sepp Nen T" first="Tapio" last="Sepp Nen">Tapio Sepp Nen</name><affiliation wicri:level="1"><country xml:lang="fr">Finlande</country><wicri:regionArea>MediaTeam Oulu, University of Oulu, P.O.BOX 4500, FIN-90014</wicri:regionArea><wicri:noRegion>FIN-90014</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Finlande</country></affiliation></author><author><name sortKey="Penttil, Jani" sort="Penttil, Jani" uniqKey="Penttil J" first="Jani" last="Penttil">Jani Penttil</name><affiliation wicri:level="1"><country xml:lang="fr">Finlande</country><wicri:regionArea>VTT Technical Research Centre of Finland, Kaitoväylä 1, P.O. Box 1100, FIN-90571, Oulu</wicri:regionArea><wicri:noRegion>Oulu</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Finlande</country></affiliation></author><author><name sortKey="Peltola, Johannes" sort="Peltola, Johannes" uniqKey="Peltola J" first="Johannes" last="Peltola">Johannes Peltola</name><affiliation wicri:level="1"><country xml:lang="fr">Finlande</country><wicri:regionArea>VTT Technical Research Centre of Finland, Kaitoväylä 1, P.O. Box 1100, FIN-90571, Oulu</wicri:regionArea><wicri:noRegion>Oulu</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Finlande</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="ISSN">0302-9743</idno></series><idno type="istex">0B6CD3EE5AB28BFF813BE4D282217527E35EDD21</idno><idno type="DOI">10.1007/3-540-45113-7_26</idno><idno type="ChapterID">26</idno><idno type="ChapterID">Chap26</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: In this paper we describe new methods to detect semantic concepts from digital video based on audible and visual content. Temporal Gradient Correlogram captures temporal correlations of gradient edge directions from sampled shot frames. Power-related physical features are extracted from short audio samples in video shots. Video shots containing people, cityscape, landscape, speech or instrumental sound are detected with trained self-organized maps and kNN classification results of audio samples. Test runs and evaluations in TREC 2002 Video Track show consistent performance for Temporal Gradient Correlogram and state-of-the-art precision in audio-based instrumental sound detection.</div></front></TEI><affiliations><list><country><li>Finlande</li></country></list><tree><country name="Finlande"><noRegion><name sortKey="Rautiainen, Mika" sort="Rautiainen, Mika" uniqKey="Rautiainen M" first="Mika" last="Rautiainen">Mika Rautiainen</name></noRegion><name sortKey="Peltola, Johannes" sort="Peltola, Johannes" uniqKey="Peltola J" first="Johannes" last="Peltola">Johannes Peltola</name><name sortKey="Peltola, Johannes" sort="Peltola, Johannes" uniqKey="Peltola J" first="Johannes" last="Peltola">Johannes Peltola</name><name sortKey="Penttil, Jani" sort="Penttil, Jani" uniqKey="Penttil J" first="Jani" last="Penttil">Jani Penttil</name><name sortKey="Penttil, Jani" sort="Penttil, Jani" uniqKey="Penttil J" first="Jani" last="Penttil">Jani Penttil</name><name sortKey="Rautiainen, Mika" sort="Rautiainen, Mika" uniqKey="Rautiainen M" first="Mika" last="Rautiainen">Mika Rautiainen</name><name sortKey="Sepp Nen, Tapio" sort="Sepp Nen, Tapio" uniqKey="Sepp Nen T" first="Tapio" last="Sepp Nen">Tapio Sepp Nen</name><name sortKey="Sepp Nen, Tapio" sort="Sepp Nen, Tapio" uniqKey="Sepp Nen T" first="Tapio" last="Sepp Nen">Tapio Sepp Nen</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 001728 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001728 | 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:0B6CD3EE5AB28BFF813BE4D282217527E35EDD21
|texte= Detecting Semantic Concepts from Video Using Temporal Gradients and Audio Classification
}}
| This area was generated with Dilib version V0.6.32. |  |