University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Heterogeneous Feature Selection with Multi-Modal Deep Neural Networks and Sparse Group Lasso

Zhao, L, Hu, Q and Wang, W (2015) Heterogeneous Feature Selection with Multi-Modal Deep Neural Networks and Sparse Group Lasso IEEE Transactions on Multimedia, 17 (11). pp. 1936-1948.

[img] Text (Acceptance)
ZhaoHW_TMM_2015_acceptanceletter.pdf - Other
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (47kB)
[img]
Preview
Text
Zhao_WH_TMM_2015.pdf
Available under License : See the attached licence file.

Download (4MB) | Preview
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

Heterogeneous feature representations are widely used in machine learning and pattern recognition, especially for multimedia analysis. The multi-modal, often also highdimensional, features may contain redundant and irrelevant information that can deteriorate the performance of modeling in classification. It is a challenging problem to select the informative features for a given task from the redundant and heterogeneous feature groups. In this paper, we propose a novel framework to address this problem. This framework is composed of two modules, namely, multi-modal deep neural networks and feature selection with sparse group LASSO. Given diverse groups of discriminative features, the proposed technique first converts the multi-modal data into a unified representation with different branches of the multi-modal deep neural networks. Then, through solving a sparse group LASSO problem, the feature selection component is used to derive a weight vector to indicate the importance of the feature groups. Finally, the feature groups with large weights are considered more relevant and hence are selected. We evaluate our framework on three image classification datasets. Experimental results show that the proposed approach is effective in selecting the relevant feature groups and achieves competitive classification performance as compared with several recent baseline methods.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Zhao, LUNSPECIFIEDUNSPECIFIED
Hu, QUNSPECIFIEDUNSPECIFIED
Wang, WUNSPECIFIEDUNSPECIFIED
Date : 7 September 2015
Identification Number : 10.1109/TMM.2015.2477058
Additional Information : © 20105 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Depositing User : Symplectic Elements
Date Deposited : 28 Oct 2015 11:14
Last Modified : 28 Oct 2015 11:14
URI: http://epubs.surrey.ac.uk/id/eprint/809039

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800