Attribute hashing for zero-shot image retrieval

Xu, Y; Yang, Y; Shen, F; Xu, X; Zhou, Y; Shen, HT

Attribute hashing for zero-shot image retrieval

Xu, Y Yang, Y Shen, F Xu, X Zhou, Y Shen, HT

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings - IEEE International Conference on Multimedia and Expo, 2017, pp. 133 - 138
Issue Date:: 2017-08-28

Closed Access

	Filename	Description	Size
	08019425.pdf	Published version	165.2 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	Xu, Y	en_US
dc.contributor.author	Yang, Y	en_US
dc.contributor.author	Shen, F	en_US
dc.contributor.author	Xu, X	en_US
dc.contributor.author	Zhou, Y	en_US
dc.contributor.author	Shen, HT	en_US
dc.date.issued	2017-08-28	en_US
dc.identifier.citation	Proceedings - IEEE International Conference on Multimedia and Expo, 2017, pp. 133 - 138	en_US
dc.identifier.isbn	9781509060672	en_US
dc.identifier.issn	1945-7871	en_US
dc.identifier.uri	http://hdl.handle.net/10453/126575
dc.description.abstract	© 2017 IEEE. Hashing has been recognized as one of the most promising ways in indexing and retrieving high-dimensional data due to the excellent merits in efficiency and effectiveness. Nevertheless, most existing approaches inevitably suffer from the problem of 'semantic gap', especially when facing the rapid evolution of newly-emerging 'unseen' categories on the Web. In this work, we propose an innovative approach, termed Attribute Hashing (AH), to facilitate zero-shot image retrieval (i.e., query by 'unseen' images). In particular, we propose a multi-layer hierarchy for hashing, which fully exploits attributes to model the relationships among visual features, binary codes and labels. Besides, we deliberately preserve the nature of hash codes (i.e., discreteness and local structure) to the greatest extent. We conduct extensive experiments on several real-world image datasets to show the superiority of our proposed AH approach as compared to the state-of-the-arts.	en_US
dc.relation.ispartof	Proceedings - IEEE International Conference on Multimedia and Expo	en_US
dc.relation.isbasedon	10.1109/ICME.2017.8019425	en_US
dc.title	Attribute hashing for zero-shot image retrieval	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	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
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Software
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2017 IEEE. Hashing has been recognized as one of the most promising ways in indexing and retrieving high-dimensional data due to the excellent merits in efficiency and effectiveness. Nevertheless, most existing approaches inevitably suffer from the problem of 'semantic gap', especially when facing the rapid evolution of newly-emerging 'unseen' categories on the Web. In this work, we propose an innovative approach, termed Attribute Hashing (AH), to facilitate zero-shot image retrieval (i.e., query by 'unseen' images). In particular, we propose a multi-layer hierarchy for hashing, which fully exploits attributes to model the relationships among visual features, binary codes and labels. Besides, we deliberately preserve the nature of hash codes (i.e., discreteness and local structure) to the greatest extent. We conduct extensive experiments on several real-world image datasets to show the superiority of our proposed AH approach as compared to the state-of-the-arts.

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

http://hdl.handle.net/10453/126575