Learning to focus for object proposals

Chen, Z; You, X; Li, J

Learning to focus for object proposals

Chen, Z You, X Li, J

Permalink

Publication Type:: Conference Proceeding
Citation:: 2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017, 2018, 2018-January pp. 439 - 444
Issue Date:: 2018-02-27

Closed Access

	Filename	Description	Size
	Learning to focus for object proposals.pdf	Published version	487.37 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	Chen, Z	en_US
dc.contributor.author	You, X	en_US
dc.contributor.author	Li, J https://orcid.org/0000-0002-1336-2241	en_US
dc.date.issued	2018-02-27	en_US
dc.identifier.citation	2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017, 2018, 2018-January pp. 439 - 444	en_US
dc.identifier.isbn	9781538630167	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134212
dc.description.abstract	© 2017 IEEE. Object proposal generators address the wasteful exhaustive search of the sliding window scheme in visual object detection and have been shown effective. However, the number of candidate windows is still large in order to ensure full coverage of potential objects. This paper presents a complementary technique that aims to work with any proposal generating system, amending the workflow from 'propose-assess' to 'propose-adjust-assess'. The adjustment serves as an auto-focus mechanism for the system and reduces the number of object proposals to be processed. The auto-focus is realized by two learning-based transformation models, one translating and the other deforming the windows towards better alignments of the objects, which are trained for identifying generic objects using image cues. Experiments on reallife image data sets show that the proposed technique can reduce the number of proposals without loss of performance.	en_US
dc.relation.ispartof	2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017	en_US
dc.relation.isbasedon	10.1109/SPAC.2017.8304319	en_US
dc.title	Learning to focus for object proposals	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-January	en_US
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 Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	2018-January	en_US

Abstract:

© 2017 IEEE. Object proposal generators address the wasteful exhaustive search of the sliding window scheme in visual object detection and have been shown effective. However, the number of candidate windows is still large in order to ensure full coverage of potential objects. This paper presents a complementary technique that aims to work with any proposal generating system, amending the workflow from 'propose-assess' to 'propose-adjust-assess'. The adjustment serves as an auto-focus mechanism for the system and reduces the number of object proposals to be processed. The auto-focus is realized by two learning-based transformation models, one translating and the other deforming the windows towards better alignments of the objects, which are trained for identifying generic objects using image cues. Experiments on reallife image data sets show that the proposed technique can reduce the number of proposals without loss of performance.

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

http://hdl.handle.net/10453/134212