A multi modal approach to gesture recognition from audio and video data

Bayer, Immanuel; Silbermann, Thierry

A multi modal approach to gesture recognition from audio and video data

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2013

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

Proceedings of the 15th ACM on International conference on multimodal interaction - ICMI '13. New York, New York, USA: ACM Press, 2013, pp. 461-466. ISBN 978-1-4503-2129-7. Available under: doi: 10.1145/2522848.2532592

Zusammenfassung

We describe in this paper our approach for the Multi-modal gesture recognition challenge organized by ChaLearn in conjunction with the ICMI 2013 conference. The competition's task was to learn a vocabulary of 20 types of Italian gestures performed from different persons and to detect them in sequences. We develop an algorithm to find the gesture intervals in the audio data, extract audio features from those intervals and train two different models. We engineer features from the skeleton data and use the gesture intervals in the training data to train a model that we afterwards apply to the test sequences using a sliding window. We combine the models through weighted averaging. We find that this way to combine information from two different sources boosts the models performance significantly.

Fachgebiet (DDC)

004 Informatik

Konferenz

the 15th ACM, 9. Dez. 2013 - 13. Dez. 2013, Sydney, Australia

Zitieren

ISO 690

BAYER, Immanuel, Thierry SILBERMANN, 2013. A multi modal approach to gesture recognition from audio and video data. the 15th ACM. Sydney, Australia, 9. Dez. 2013 - 13. Dez. 2013. In: Proceedings of the 15th ACM on International conference on multimodal interaction - ICMI '13. New York, New York, USA: ACM Press, 2013, pp. 461-466. ISBN 978-1-4503-2129-7. Available under: doi: 10.1145/2522848.2532592

BibTex

@inproceedings{Bayer2013multi-26475,
  year={2013},
  doi={10.1145/2522848.2532592},
  title={A multi modal approach to gesture recognition from audio and video data},
  isbn={978-1-4503-2129-7},
  publisher={ACM Press},
  address={New York, New York, USA},
  booktitle={Proceedings of the 15th ACM on International conference on multimodal interaction - ICMI '13},
  pages={461--466},
  author={Bayer, Immanuel and Silbermann, Thierry}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/26475">
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/26475"/>
    <dc:language>eng</dc:language>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Silbermann, Thierry</dc:creator>
    <dcterms:title>A multi modal approach to gesture recognition from audio and video data</dcterms:title>
    <dcterms:issued>2013</dcterms:issued>
    <dcterms:bibliographicCitation>Proceedings of the 15th ACM International conference on multimodal interaction : Sydney, NSW, Australia ; December 09 - 13, 2013 / Julien Epps ... (eds.). - New York : ACM, 2013. - S. 461-466. - ISBN 978-1-4503-2129-7</dcterms:bibliographicCitation>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-02-25T09:52:37Z</dcterms:available>
    <dc:contributor>Silbermann, Thierry</dc:contributor>
    <dc:contributor>Bayer, Immanuel</dc:contributor>
    <dc:creator>Bayer, Immanuel</dc:creator>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-02-25T09:52:37Z</dc:date>
    <dcterms:abstract xml:lang="eng">We describe in this paper our approach for the Multi-modal gesture recognition challenge organized by ChaLearn in conjunction with the ICMI 2013 conference. The competition's task was to learn a vocabulary of 20 types of Italian gestures performed from different persons and to detect them in sequences. We develop an algorithm to find the gesture intervals in the audio data, extract audio features from those intervals and train two different models. We engineer features from the skeleton data and use the gesture intervals in the training data to train a model that we afterwards apply to the test sequences using a sliding window. We combine the models through weighted averaging. We find that this way to combine information from two different sources boosts the models performance significantly.</dcterms:abstract>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja