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

Tutkimustuotos › › vertaisarvioitu

Standard

Dynamic action classification based on iterative data selection and Feedforward Neural networks. / Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis.

European Signal Processing Conference. European Signal Processing Conference, EUSIPCO, 2013. 6811572.

Tutkimustuotos › › vertaisarvioitu

Harvard

Iosifidis, A, Tefas, A & Pitas, I 2013, Dynamic action classification based on iterative data selection and Feedforward Neural networks. julkaisussa European Signal Processing Conference., 6811572, European Signal Processing Conference, EUSIPCO, Marrakech, Marokko, 9/09/13.

APA

Iosifidis, A., Tefas, A., & Pitas, I. (2013). Dynamic action classification based on iterative data selection and Feedforward Neural networks. teoksessa European Signal Processing Conference [6811572] European Signal Processing Conference, EUSIPCO.

Vancouver

Iosifidis A, Tefas A, Pitas I. Dynamic action classification based on iterative data selection and Feedforward Neural networks. julkaisussa European Signal Processing Conference. European Signal Processing Conference, EUSIPCO. 2013. 6811572

Author

Iosifidis, Alexandros ; Tefas, Anastasios ; Pitas, Ioannis. / Dynamic action classification based on iterative data selection and Feedforward Neural networks. European Signal Processing Conference. European Signal Processing Conference, EUSIPCO, 2013.

Bibtex - Lataa

@inproceedings{3af90c37e389443c871aca7f1d55bdd0,

title = "Dynamic action classification based on iterative data selection and Feedforward Neural networks",

abstract = "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.",

keywords = "Data selection, Dynamic classification, Extreme Learning Machine, Feedforward Neural network",

author = "Alexandros Iosifidis and Anastasios Tefas and Ioannis Pitas",

year = "2013",

language = "English",

isbn = "9780992862602",

booktitle = "European Signal Processing Conference",

publisher = "European Signal Processing Conference, EUSIPCO",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Dynamic action classification based on iterative data selection and Feedforward Neural networks

AU - Iosifidis, Alexandros

AU - Tefas, Anastasios

AU - Pitas, Ioannis

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - Data selection

KW - Dynamic classification

KW - Extreme Learning Machine

KW - Feedforward Neural network

M3 - Conference contribution

SN - 9780992862602

BT - European Signal Processing Conference

PB - European Signal Processing Conference, EUSIPCO

ER -

TUTCRIS