Audiovisual behavior modeling by combined feature spaces

Björn Schuller, Dejan Arsic, Gerhard Rigoll, Matthias Wimmer, Bernd Radig

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

67 Zitate (Scopus)

Abstract

Great interest is recently shown in behavior modeling, especially in public surveillance tasks. In general it is agreed upon the benefits of use of several input cues as audio and video. Yet, synchronization and fusion of these information sources remains the main challenge. We therefore show results for a feature space combination, which allows for overall feature space optimization. Audio and video features are thereby firstly derived as Low-Level-Descriptors. Synchronization and feature combination is achieved by multivariate time-series analysis. Test-runs on a database of aggressive, cheerful, intoxicated, nervous, neutral, and tired behavior in an airplane situation show a significant improvement over each single modality.

OriginalspracheEnglisch
Titel2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten733-736
Seitenumfang4
ISBN (Print)1424407281, 9781424407286
DOIs
PublikationsstatusVeröffentlicht - 2007
Veranstaltung2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, USA/Vereinigte Staaten
Dauer: 15 Apr. 200720 Apr. 2007

Publikationsreihe

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Band2
ISSN (Print)1520-6149

Konferenz

Konferenz2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Land/GebietUSA/Vereinigte Staaten
OrtHonolulu, HI
Zeitraum15/04/0720/04/07

Fingerprint

Untersuchen Sie die Forschungsthemen von „Audiovisual behavior modeling by combined feature spaces“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren