Beyond Covariance: SICE and Kernel Based Visual Feature Representation

Zhang, J; Wang, L; Zhou, L; Li, W

Beyond Covariance: SICE and Kernel Based Visual Feature Representation

Zhang, J

Wang, L Zhou, L Li, W

Permalink

Publisher:: Springer Science and Business Media LLC
Publication Type:: Journal Article
Citation:: International Journal of Computer Vision, 2020, pp. 1-21
Issue Date:: 2020-01-01

Closed Access

	Filename	Description	Size
	Zhang2020_Article_BeyondCovarianceSICEAndKernelB.pdf	Published version	1 MB	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	Zhang, J https://orcid.org/0000-0001-5048-5606
dc.contributor.author	Wang, L
dc.contributor.author	Zhou, L
dc.contributor.author	Li, W
dc.date.accessioned	2020-11-06T19:08:25Z
dc.date.available	2020-11-06T19:08:25Z
dc.date.issued	2020-01-01
dc.identifier.citation	International Journal of Computer Vision, 2020, pp. 1-21
dc.identifier.issn	0920-5691
dc.identifier.issn	1573-1405
dc.identifier.uri	http://hdl.handle.net/10453/143798
dc.description.abstract	© 2020, Springer Science+Business Media, LLC, part of Springer Nature. The past several years have witnessed increasing research interest on covariance-based feature representation. Originally proposed as a region descriptor, it has now been used as a general representation in various recognition tasks, demonstrating promising performance. However, covariance matrix has some inherent shortcomings such as singularity in the case of small sample, limited capability in modeling complicated feature relationship, and a single, fixed form of representation. To achieve better recognition performance, this paper argues that more capable and flexible symmetric positive definite (SPD)-matrix-based representation shall be explored, and this is attempted in this work by exploiting prior knowledge of data and nonlinear representation. Specifically, to better deal with the issues of small number of feature vectors and high feature dimensionality, we propose to exploit the structure sparsity of visual features and exemplify sparse inverse covariance estimate as a new feature representation. Furthermore, to effectively model complicated feature relationship, we propose to directly compute kernel matrix over feature dimensions, leading to a robust, flexible and open framework of SPD-matrix-based representation. Through theoretical analysis and experimental study, the proposed two representations well demonstrate their advantages over the covariance counterpart in skeletal human action recognition, image set classification and object classification tasks.
dc.language	en
dc.publisher	Springer Science and Business Media LLC
dc.relation.ispartof	International Journal of Computer Vision
dc.relation.isbasedon	10.1007/s11263-020-01376-1
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Beyond Covariance: SICE and Kernel Based Visual Feature Representation
dc.type	Journal Article
utslib.for	0801 Artificial Intelligence and Image Processing
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2020-11-06T19:08:22Z
pubs.publication-status	Published

Abstract:

© 2020, Springer Science+Business Media, LLC, part of Springer Nature. The past several years have witnessed increasing research interest on covariance-based feature representation. Originally proposed as a region descriptor, it has now been used as a general representation in various recognition tasks, demonstrating promising performance. However, covariance matrix has some inherent shortcomings such as singularity in the case of small sample, limited capability in modeling complicated feature relationship, and a single, fixed form of representation. To achieve better recognition performance, this paper argues that more capable and flexible symmetric positive definite (SPD)-matrix-based representation shall be explored, and this is attempted in this work by exploiting prior knowledge of data and nonlinear representation. Specifically, to better deal with the issues of small number of feature vectors and high feature dimensionality, we propose to exploit the structure sparsity of visual features and exemplify sparse inverse covariance estimate as a new feature representation. Furthermore, to effectively model complicated feature relationship, we propose to directly compute kernel matrix over feature dimensions, leading to a robust, flexible and open framework of SPD-matrix-based representation. Through theoretical analysis and experimental study, the proposed two representations well demonstrate their advantages over the covariance counterpart in skeletal human action recognition, image set classification and object classification tasks.

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

http://hdl.handle.net/10453/143798