Multitask Autoencoder Model for Recovering Human Poses

Yu, J; Hong, C; Rui, Y; Tao, D

Multitask Autoencoder Model for Recovering Human Poses

Yu, J Hong, C Rui, Y Tao, D

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Industrial Electronics, 2018, 65 (6), pp. 5060 - 5068
Issue Date:: 2018-06-01

Closed Access

	Filename	Description	Size
	08010362.pdf	Published Version	703.37 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	Yu, J	en_US
dc.contributor.author	Hong, C	en_US
dc.contributor.author	Rui, Y	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2018-06-01	en_US
dc.identifier.citation	IEEE Transactions on Industrial Electronics, 2018, 65 (6), pp. 5060 - 5068	en_US
dc.identifier.issn	0278-0046	en_US
dc.identifier.uri	http://hdl.handle.net/10453/123848
dc.description.abstract	© 1982-2012 IEEE. Human pose recovery in videos is usually conducted by matching 2-D image features and retrieving relevant 3-D human poses. In the retrieving process, the mapping between images and poses is critical. Traditional methods assume this mapping relationship as local joint detection or global joint localization, which limits recovery performance of these methods since this two tasks are actually unified. In this paper, we propose a novel pose recovery framework by simultaneously learning the tasks of joint localization and joint detection. To obtain this framework, multiple manifold learning is used and the shared parameter is calculated. With them, multiple manifold regularizers are integrated and generalized eigendecomposition is utilized to achieve parameter optimization. In this way, pose recovery is boosted by both global mapping and local refinement. Experimental results on two popular datasets demonstrates that the recovery error has been reduced by 10%-20%, which proves the performance improvement of the proposed method.	en_US
dc.relation.ispartof	IEEE Transactions on Industrial Electronics	en_US
dc.relation.isbasedon	10.1109/TIE.2017.2739691	en_US
dc.subject.classification	Electrical & Electronic Engineering	en_US
dc.title	Multitask Autoencoder Model for Recovering Human Poses	en_US
dc.type	Journal Article
utslib.citation.volume	6	en_US
utslib.citation.volume	65	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	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	6	en_US
pubs.publication-status	Published	en_US
pubs.volume	65	en_US

Abstract:

© 1982-2012 IEEE. Human pose recovery in videos is usually conducted by matching 2-D image features and retrieving relevant 3-D human poses. In the retrieving process, the mapping between images and poses is critical. Traditional methods assume this mapping relationship as local joint detection or global joint localization, which limits recovery performance of these methods since this two tasks are actually unified. In this paper, we propose a novel pose recovery framework by simultaneously learning the tasks of joint localization and joint detection. To obtain this framework, multiple manifold learning is used and the shared parameter is calculated. With them, multiple manifold regularizers are integrated and generalized eigendecomposition is utilized to achieve parameter optimization. In this way, pose recovery is boosted by both global mapping and local refinement. Experimental results on two popular datasets demonstrates that the recovery error has been reduced by 10%-20%, which proves the performance improvement of the proposed method.

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

http://hdl.handle.net/10453/123848