TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Dynamic action classification based on iterative data selection and Feedforward Neural networks

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoEuropean Signal Processing Conference
KustantajaEuropean Signal Processing Conference, EUSIPCO
ISBN (painettu)9780992862602
TilaJulkaistu - 2013
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
Tapahtuma2013 21st European Signal Processing Conference, EUSIPCO 2013 - Marrakech, Marokko
Kesto: 9 syyskuuta 201313 syyskuuta 2013

Conference

Conference2013 21st European Signal Processing Conference, EUSIPCO 2013
MaaMarokko
KaupunkiMarrakech
Ajanjakso9/09/1313/09/13

Tiivistelmä

In this paper we present a dynamic classification scheme involving Single-hidden Layer Feedforward Neural (SLFN) network-based non-linear data mapping and test sample-specific labeled data selection in multiple levels. The number of levels is dynamically determined by the test sample under consideration, while the use of Extreme Learning Machine (ELM) algorithm for SLFN network training leads to fast operation. The proposed dynamic classification scheme has been applied to human action recognition by employing the Bag of Visual Words (BoVW)-based action video representation providing enhanced classification performance compared to the static classification approach.

Tutkimusalat