Tampere University of Technology

TUTCRIS Research Portal

Multimodal subspace support vector data description

Research output: Contribution to journalArticleScientificpeer-review

Standard

Multimodal subspace support vector data description. / Sohrab, Fahad; Raitoharju, Jenni; Iosifidis, Alexandros; Gabbouj, Moncef.

In: Pattern Recognition, Vol. 110, 107648, 2020.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Sohrab, F, Raitoharju, J, Iosifidis, A & Gabbouj, M 2020, 'Multimodal subspace support vector data description', Pattern Recognition, vol. 110, 107648. https://doi.org/10.1016/j.patcog.2020.107648

APA

Vancouver

Author

Sohrab, Fahad ; Raitoharju, Jenni ; Iosifidis, Alexandros ; Gabbouj, Moncef. / Multimodal subspace support vector data description. In: Pattern Recognition. 2020 ; Vol. 110.

Bibtex - Download

@article{171117d80f95457e93cb8102add38673,
title = "Multimodal subspace support vector data description",
abstract = "In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification. The proposed method iteratively transforms the data from the original feature space of each modality to a new common feature space along with finding a joint compact description of data coming from all the modalities. For data in each modality, we define a separate transformation to map the data from the corresponding feature space to the new optimized subspace by exploiting the available information from the class of interest only. We also propose different regularization strategies for the proposed method and provide both linear and non-linear formulations. The proposed Multimodal Subspace Support Vector Data Description outperforms all the competing methods using data from a single modality or fusing data from all modalities in four out of five datasets.",
keywords = "Feature transformation, Multimodal data, One-class classification, Subspace learning, Support vector data description",
author = "Fahad Sohrab and Jenni Raitoharju and Alexandros Iosifidis and Moncef Gabbouj",
note = "EXT={"}Iosifidis, Alexandros{"}",
year = "2020",
doi = "10.1016/j.patcog.2020.107648",
language = "English",
volume = "110",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "ELSEVIER SCI LTD",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Multimodal subspace support vector data description

AU - Sohrab, Fahad

AU - Raitoharju, Jenni

AU - Iosifidis, Alexandros

AU - Gabbouj, Moncef

N1 - EXT="Iosifidis, Alexandros"

PY - 2020

Y1 - 2020

N2 - In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification. The proposed method iteratively transforms the data from the original feature space of each modality to a new common feature space along with finding a joint compact description of data coming from all the modalities. For data in each modality, we define a separate transformation to map the data from the corresponding feature space to the new optimized subspace by exploiting the available information from the class of interest only. We also propose different regularization strategies for the proposed method and provide both linear and non-linear formulations. The proposed Multimodal Subspace Support Vector Data Description outperforms all the competing methods using data from a single modality or fusing data from all modalities in four out of five datasets.

AB - In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification. The proposed method iteratively transforms the data from the original feature space of each modality to a new common feature space along with finding a joint compact description of data coming from all the modalities. For data in each modality, we define a separate transformation to map the data from the corresponding feature space to the new optimized subspace by exploiting the available information from the class of interest only. We also propose different regularization strategies for the proposed method and provide both linear and non-linear formulations. The proposed Multimodal Subspace Support Vector Data Description outperforms all the competing methods using data from a single modality or fusing data from all modalities in four out of five datasets.

KW - Feature transformation

KW - Multimodal data

KW - One-class classification

KW - Subspace learning

KW - Support vector data description

U2 - 10.1016/j.patcog.2020.107648

DO - 10.1016/j.patcog.2020.107648

M3 - Article

VL - 110

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

M1 - 107648

ER -