Large sparse cone non-negative matrix factorization for image annotation

Tao, D; Li, X; Gao, X

Large sparse cone non-negative matrix factorization for image annotation

Tao, D

Li, X Gao, X

Permalink

Publication Type:: Journal Article
Citation:: ACM Transactions on Intelligent Systems and Technology, 2017, 8 (3)
Issue Date:: 2017-04-01

Closed Access

	Filename	Description	Size
	a37-tao.pdf	Published Version	711.84 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Li, X	en_US
dc.contributor.author	Gao, X	en_US
dc.date.issued	2017-04-01	en_US
dc.identifier.citation	ACM Transactions on Intelligent Systems and Technology, 2017, 8 (3)	en_US
dc.identifier.issn	2157-6904	en_US
dc.identifier.uri	http://hdl.handle.net/10453/123841
dc.description.abstract	© 2017 ACM. Image annotation assigns relevant tags to query images based on their semantic contents. Since Non-negative Matrix Factorization (NMF) has the strong ability to learn parts-based representations, recently, a number of algorithms based on NMF have been proposed for image annotation and have achieved good performance. However, most of the efforts have focused on the representations of images and annotations. The properties of the semantic parts have not been well studied. In this article, we revisit the sparseness-constrained NMF (sNMF) proposed by Hoyer [2004]. By endowing the sparseness constraint with a geometric interpretation and sNMF with theoretical analyses of the generalization ability, we show that NMF with such a sparseness constraint has three advantages for image annotation tasks: (i) The sparseness constraint is more ℓ0-norm oriented than the ℓ1-norm-based sparseness, which significantly enhances the ability of NMF to robustly learn semantic parts. (ii) The sparseness constraint has a large cone interpretation and thus allows the reconstruction error of NMF to be smaller, which means that the learned semantic parts are more powerful to represent images for tagging. (iii) The learned semantic parts are less correlated, which increases the discriminative ability for annotating images. Moreover, we present a new efficient large sparse cone NMF (LsCNMF) algorithm to optimize the sNMF problem by employing the Nesterov's optimal gradient method. We conducted experiments on the PASCAL VOC07 dataset and demonstrated the effectiveness of LsCNMF for image annotation.	en_US
dc.relation.ispartof	ACM Transactions on Intelligent Systems and Technology	en_US
dc.relation.isbasedon	10.1145/2987379	en_US
dc.title	Large sparse cone non-negative matrix factorization for image annotation	en_US
dc.type	Journal Article
utslib.citation.volume	3	en_US
utslib.citation.volume	8	en_US
utslib.for	0802 Computation Theory and Mathematics	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0806 Information Systems	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	3	en_US
pubs.publication-status	Published	en_US
pubs.volume	8	en_US

Abstract:

© 2017 ACM. Image annotation assigns relevant tags to query images based on their semantic contents. Since Non-negative Matrix Factorization (NMF) has the strong ability to learn parts-based representations, recently, a number of algorithms based on NMF have been proposed for image annotation and have achieved good performance. However, most of the efforts have focused on the representations of images and annotations. The properties of the semantic parts have not been well studied. In this article, we revisit the sparseness-constrained NMF (sNMF) proposed by Hoyer [2004]. By endowing the sparseness constraint with a geometric interpretation and sNMF with theoretical analyses of the generalization ability, we show that NMF with such a sparseness constraint has three advantages for image annotation tasks: (i) The sparseness constraint is more ℓ0-norm oriented than the ℓ1-norm-based sparseness, which significantly enhances the ability of NMF to robustly learn semantic parts. (ii) The sparseness constraint has a large cone interpretation and thus allows the reconstruction error of NMF to be smaller, which means that the learned semantic parts are more powerful to represent images for tagging. (iii) The learned semantic parts are less correlated, which increases the discriminative ability for annotating images. Moreover, we present a new efficient large sparse cone NMF (LsCNMF) algorithm to optimize the sNMF problem by employing the Nesterov's optimal gradient method. We conducted experiments on the PASCAL VOC07 dataset and demonstrated the effectiveness of LsCNMF for image annotation.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/123841