Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition (Extended Abstract)

Yang, X; Liu, W; Liu, W

Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition (Extended Abstract)

Yang, X Liu, W

Liu, W

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2023 IEEE 39th International Conference on Data Engineering (ICDE), 2023, 2023-April, pp. 3835-3836
Issue Date:: 2023-07-26

Embargoed

	Filename	Description	Size
	Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition.pdf	Accepted version	237.98 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 26 Jul 2025

Full metadata record

Field	Value	Language
dc.contributor.author	Yang, X
dc.contributor.author	Liu, W https://orcid.org/0000-0002-3003-1313
dc.contributor.author	Liu, W https://orcid.org/0000-0002-3003-1313
dc.date	2023-04-03
dc.date.accessioned	2024-01-31T22:51:40Z
dc.date.available	2024-01-31T22:51:40Z
dc.date.issued	2023-07-26
dc.identifier.citation	2023 IEEE 39th International Conference on Data Engineering (ICDE), 2023, 2023-April, pp. 3835-3836
dc.identifier.isbn	9798350322279
dc.identifier.issn	1084-4627
dc.identifier.uri	http://hdl.handle.net/10453/175158
dc.description.abstract	Remote sensing RS images are frequently observed from multiviews In this paper we propose the tensor canonical correlation analysis network TCCANet to tackle the multiview RS recognition problem Particularly TCCANet learns filter banks by simultaneously maximizing arbitrary number of views with high order correlation and solves the optimization problem by decomposing a covariance tensor After the convolutional stage we utilize binarization and block wise histogram strategies to generate the final feature Furthermore we also develop a Multiple Scale version of TCCANet i e MS TCCANet to extract enriched representation of the RS data by incorporating all previous convolutional layers Numerical experiment results on RSSCN7 and SAT 6 datasets demonstrate the advantages of TCCANet and MS TCCANet for RS scene recognition
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2023 IEEE 39th International Conference on Data Engineering (ICDE)
dc.relation.ispartof	2023 IEEE 39th International Conference on Data Engineering
dc.relation.isbasedon	10.1109/icde55515.2023.00344
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition (Extended Abstract)
dc.type	Conference Proceeding
utslib.citation.volume	2023-April
utslib.location.activity	Anaheim, CA, USA
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - AAI - Advanced Analytics Institute Research Centre
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2025-07-26T00:00:00+1000Z
dc.date.updated	2024-01-31T22:51:39Z
pubs.finish-date	2023-04-07
pubs.publication-status	Published
pubs.start-date	2023-04-03
pubs.volume	2023-April

Abstract:

Remote sensing RS images are frequently observed from multiviews In this paper we propose the tensor canonical correlation analysis network TCCANet to tackle the multiview RS recognition problem Particularly TCCANet learns filter banks by simultaneously maximizing arbitrary number of views with high order correlation and solves the optimization problem by decomposing a covariance tensor After the convolutional stage we utilize binarization and block wise histogram strategies to generate the final feature Furthermore we also develop a Multiple Scale version of TCCANet i e MS TCCANet to extract enriched representation of the RS data by incorporating all previous convolutional layers Numerical experiment results on RSSCN7 and SAT 6 datasets demonstrate the advantages of TCCANet and MS TCCANet for RS scene recognition

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

http://hdl.handle.net/10453/175158