An Evolutionary Approach for Learning Motion Class Patterns
Identifieur interne : 000768 ( Main/Curation ); précédent : 000767; suivant : 000769An Evolutionary Approach for Learning Motion Class Patterns
Auteurs : Meinard Müller [Allemagne] ; Bastian Demuth [Allemagne] ; Bodo Rosenhahn [Allemagne]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2008.
English descriptors
- Teeft :
- Additional element, Algorithm, Alternative feature vectors, Col1, Col1 col2, Computer animation, Computer vision, Correct motions, Current population, Early convergence, Evolutionary approach, Evolutionary process, Expectation value, Feat, Feat feat1, Feat1, Feat1 feat2, Feat2, Feature function, Feature sequence, Feature vectors, Fourth column, Fuzzy queries, Fuzzy query, Fuzzy sets, Genetic algorithm, Human motion, Initial population, Matrix, Mocap, Mocap data, Mocap data stream, Motion class, Motion class pattern, Motion class patterns, Motion classes, Motion retrieval, Mutation, Negative training motions, Next generation, Parent individuals, Positive training motions, Precision values, Query, Recombination, Recombination step, Reference motion, Relational feature, Relational features, Reproduction process, Retrieval, Retrieval performance, Retrieval quality, Retrieval results, Right knee, Rosenhahn, Temporal variations, Tness, Tness function, Tness value, Tness values.
Abstract
Abstract: This article presents a genetic learning algorithm to derive discrete patterns that can be used for classification and retrieval of 3D motion capture data. Based on boolean motion features, the idea is to learn motion class patterns in an evolutionary process with the objective to discriminate a given set of positive from a given set of negative training motions. Here, the fitness of a pattern is measured with respect to precision and recall in a retrieval scenario, where the pattern is used as a motion query. Our experiments show that motion class patterns can automate query specification without loss of retrieval quality.
Url:
DOI: 10.1007/978-3-540-69321-5_37
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000E57
- to stream Istex, to step Curation: Pour aller vers cette notice dans l'étape Curation :000D85
- to stream Istex, to step Checkpoint: Pour aller vers cette notice dans l'étape Curation :000592
- to stream Main, to step Merge: Pour aller vers cette notice dans l'étape Curation :000768
Links to Exploration step
ISTEX:8DC325B1F4752CCCC684E1A308B8A1487A1A3E2BLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">An Evolutionary Approach for Learning Motion Class Patterns</title>
<author><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name>
</author>
<author><name sortKey="Demuth, Bastian" sort="Demuth, Bastian" uniqKey="Demuth B" first="Bastian" last="Demuth">Bastian Demuth</name>
</author>
<author><name sortKey="Rosenhahn, Bodo" sort="Rosenhahn, Bodo" uniqKey="Rosenhahn B" first="Bodo" last="Rosenhahn">Bodo Rosenhahn</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:8DC325B1F4752CCCC684E1A308B8A1487A1A3E2B</idno>
<date when="2008" year="2008">2008</date>
<idno type="doi">10.1007/978-3-540-69321-5_37</idno>
<idno type="url">https://api.istex.fr/document/8DC325B1F4752CCCC684E1A308B8A1487A1A3E2B/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000E57</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000E57</idno>
<idno type="wicri:Area/Istex/Curation">000D85</idno>
<idno type="wicri:Area/Istex/Checkpoint">000592</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000592</idno>
<idno type="wicri:doubleKey">0302-9743:2008:Muller M:an:evolutionary:approach</idno>
<idno type="wicri:Area/Main/Merge">000768</idno>
<idno type="wicri:Area/Main/Curation">000768</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">An Evolutionary Approach for Learning Motion Class Patterns</title>
<author><name sortKey="Muller, Meinard" sort="Muller, Meinard" uniqKey="Muller M" first="Meinard" last="Müller">Meinard Müller</name>
<affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country>
<wicri:regionArea>Max-Planck-Institut für Informatik, Campus E1-4, 66123, Saarbrücken</wicri:regionArea>
<placeName><region type="land" nuts="2">Sarre (Land)</region>
<settlement type="city">Sarrebruck</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Allemagne</country>
</affiliation>
</author>
<author><name sortKey="Demuth, Bastian" sort="Demuth, Bastian" uniqKey="Demuth B" first="Bastian" last="Demuth">Bastian Demuth</name>
<affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country>
<wicri:regionArea>Institut für Informatik III, Universität Bonn, Römerstr. 164, 53117, Bonn</wicri:regionArea>
<placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region>
<region type="district" nuts="2">District de Cologne</region>
<settlement type="city">Bonn</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Rosenhahn, Bodo" sort="Rosenhahn, Bodo" uniqKey="Rosenhahn B" first="Bodo" last="Rosenhahn">Bodo Rosenhahn</name>
<affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country>
<wicri:regionArea>Max-Planck-Institut für Informatik, Campus E1-4, 66123, Saarbrücken</wicri:regionArea>
<placeName><region type="land" nuts="2">Sarre (Land)</region>
<settlement type="city">Sarrebruck</settlement>
</placeName>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2008</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Additional element</term>
<term>Algorithm</term>
<term>Alternative feature vectors</term>
<term>Col1</term>
<term>Col1 col2</term>
<term>Computer animation</term>
<term>Computer vision</term>
<term>Correct motions</term>
<term>Current population</term>
<term>Early convergence</term>
<term>Evolutionary approach</term>
<term>Evolutionary process</term>
<term>Expectation value</term>
<term>Feat</term>
<term>Feat feat1</term>
<term>Feat1</term>
<term>Feat1 feat2</term>
<term>Feat2</term>
<term>Feature function</term>
<term>Feature sequence</term>
<term>Feature vectors</term>
<term>Fourth column</term>
<term>Fuzzy queries</term>
<term>Fuzzy query</term>
<term>Fuzzy sets</term>
<term>Genetic algorithm</term>
<term>Human motion</term>
<term>Initial population</term>
<term>Matrix</term>
<term>Mocap</term>
<term>Mocap data</term>
<term>Mocap data stream</term>
<term>Motion class</term>
<term>Motion class pattern</term>
<term>Motion class patterns</term>
<term>Motion classes</term>
<term>Motion retrieval</term>
<term>Mutation</term>
<term>Negative training motions</term>
<term>Next generation</term>
<term>Parent individuals</term>
<term>Positive training motions</term>
<term>Precision values</term>
<term>Query</term>
<term>Recombination</term>
<term>Recombination step</term>
<term>Reference motion</term>
<term>Relational feature</term>
<term>Relational features</term>
<term>Reproduction process</term>
<term>Retrieval</term>
<term>Retrieval performance</term>
<term>Retrieval quality</term>
<term>Retrieval results</term>
<term>Right knee</term>
<term>Rosenhahn</term>
<term>Temporal variations</term>
<term>Tness</term>
<term>Tness function</term>
<term>Tness value</term>
<term>Tness values</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: This article presents a genetic learning algorithm to derive discrete patterns that can be used for classification and retrieval of 3D motion capture data. Based on boolean motion features, the idea is to learn motion class patterns in an evolutionary process with the objective to discriminate a given set of positive from a given set of negative training motions. Here, the fitness of a pattern is measured with respect to precision and recall in a retrieval scenario, where the pattern is used as a motion query. Our experiments show that motion class patterns can automate query specification without loss of retrieval quality.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sarre/explor/MusicSarreV3/Data/Main/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000768 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Curation/biblio.hfd -nk 000768 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Sarre |area= MusicSarreV3 |flux= Main |étape= Curation |type= RBID |clé= ISTEX:8DC325B1F4752CCCC684E1A308B8A1487A1A3E2B |texte= An Evolutionary Approach for Learning Motion Class Patterns }}
This area was generated with Dilib version V0.6.33. |