TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Class-specific kernel discriminant analysis based on Cholesky decomposition

Tutkimustuotosvertaisarvioitu

Standard

Class-specific kernel discriminant analysis based on Cholesky decomposition. / Iosifidis, Alexandres; Gabbouj, Moncef.

2017 International Joint Conference on Neural Networks, IJCNN 2017. IEEE, 2017. s. 1141-1146.

Tutkimustuotosvertaisarvioitu

Harvard

Iosifidis, A & Gabbouj, M 2017, Class-specific kernel discriminant analysis based on Cholesky decomposition. julkaisussa 2017 International Joint Conference on Neural Networks, IJCNN 2017. IEEE, Sivut 1141-1146, INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, 1/01/00. https://doi.org/10.1109/IJCNN.2017.7965980

APA

Iosifidis, A., & Gabbouj, M. (2017). Class-specific kernel discriminant analysis based on Cholesky decomposition. teoksessa 2017 International Joint Conference on Neural Networks, IJCNN 2017 (Sivut 1141-1146). IEEE. https://doi.org/10.1109/IJCNN.2017.7965980

Vancouver

Iosifidis A, Gabbouj M. Class-specific kernel discriminant analysis based on Cholesky decomposition. julkaisussa 2017 International Joint Conference on Neural Networks, IJCNN 2017. IEEE. 2017. s. 1141-1146 https://doi.org/10.1109/IJCNN.2017.7965980

Author

Iosifidis, Alexandres ; Gabbouj, Moncef. / Class-specific kernel discriminant analysis based on Cholesky decomposition. 2017 International Joint Conference on Neural Networks, IJCNN 2017. IEEE, 2017. Sivut 1141-1146

Bibtex - Lataa

@inproceedings{0890b167f97f4322ad67fe48ae400190,
title = "Class-specific kernel discriminant analysis based on Cholesky decomposition",
abstract = "In this paper we describe a method for nonlinear class-specific discriminant learning that is based on Cholesky Decomposition. We show that the optimization problem solved in Class-Specific Kernel Discriminant Analysis is equivalent to that of Low-Rank Kernel Regression using training data independent target vectors. This connection allows us to devise a new Class-Specific Kernel Discriminant Analysis method that can be trained by exploiting fast linear system approaches, like the Cholesky decomposition. We verify our analysis in publicly available verification problems designed for human action recognition.",
author = "Alexandres Iosifidis and Moncef Gabbouj",
note = "jufoid=58177",
year = "2017",
month = "6",
day = "30",
doi = "10.1109/IJCNN.2017.7965980",
language = "English",
publisher = "IEEE",
pages = "1141--1146",
booktitle = "2017 International Joint Conference on Neural Networks, IJCNN 2017",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Class-specific kernel discriminant analysis based on Cholesky decomposition

AU - Iosifidis, Alexandres

AU - Gabbouj, Moncef

N1 - jufoid=58177

PY - 2017/6/30

Y1 - 2017/6/30

N2 - In this paper we describe a method for nonlinear class-specific discriminant learning that is based on Cholesky Decomposition. We show that the optimization problem solved in Class-Specific Kernel Discriminant Analysis is equivalent to that of Low-Rank Kernel Regression using training data independent target vectors. This connection allows us to devise a new Class-Specific Kernel Discriminant Analysis method that can be trained by exploiting fast linear system approaches, like the Cholesky decomposition. We verify our analysis in publicly available verification problems designed for human action recognition.

AB - In this paper we describe a method for nonlinear class-specific discriminant learning that is based on Cholesky Decomposition. We show that the optimization problem solved in Class-Specific Kernel Discriminant Analysis is equivalent to that of Low-Rank Kernel Regression using training data independent target vectors. This connection allows us to devise a new Class-Specific Kernel Discriminant Analysis method that can be trained by exploiting fast linear system approaches, like the Cholesky decomposition. We verify our analysis in publicly available verification problems designed for human action recognition.

U2 - 10.1109/IJCNN.2017.7965980

DO - 10.1109/IJCNN.2017.7965980

M3 - Conference contribution

SP - 1141

EP - 1146

BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017

PB - IEEE

ER -