Cross-domain human action recognition

Bian, W; Tao, D; Rui, Y

Cross-domain human action recognition

Bian, W Tao, D

Rui, Y

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2012, 42 (2), pp. 298 - 307
Issue Date:: 2012-04-01

Closed Access

	Filename	Description	Size
	2011005472OK.pdf		706.18 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	Bian, W	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Rui, Y	en_US
dc.date.issued	2012-04-01	en_US
dc.identifier.citation	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2012, 42 (2), pp. 298 - 307	en_US
dc.identifier.issn	1083-4419	en_US
dc.identifier.uri	http://hdl.handle.net/10453/22218
dc.description.abstract	Conventional human action recognition algorithms cannot work well when the amount of training videos is insufficient. We solve this problem by proposing a transfer topic model (TTM), which utilizes information extracted from videos in the auxiliary domain to assist recognition tasks in the target domain. The TTM is well characterized by two aspects: 1) it uses the bag-of-words model trained from the auxiliary domain to represent videos in the target domain; and 2) it assumes each human action is a mixture of a set of topics and uses the topics learned from the auxiliary domain to regularize the topic estimation in the target domain, wherein the regularization is the summation of Kullback-Leibler divergences between topic pairs of the two domains. The utilization of the auxiliary domain knowledge improves the generalization ability of the learned topic model. Experiments on Weizmann and KTH human action databases suggest the effectiveness of the proposed TTM for cross-domain human action recognition. © 2006 IEEE.	en_US
dc.relation.ispartof	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics	en_US
dc.relation.isbasedon	10.1109/TSMCB.2011.2166761	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.subject.mesh	Humans	en_US
dc.subject.mesh	Movement	en_US
dc.subject.mesh	Algorithms	en_US
dc.subject.mesh	Human Activities	en_US
dc.subject.mesh	Image Processing, Computer-Assisted	en_US
dc.subject.mesh	Video Recording	en_US
dc.subject.mesh	Databases, Factual	en_US
dc.subject.mesh	Pattern Recognition, Automated	en_US
dc.title	Cross-domain human action recognition	en_US
dc.type	Journal Article
utslib.citation.volume	2	en_US
utslib.citation.volume	42	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0102 Applied Mathematics	en_US
utslib.for	0906 Electrical and Electronic 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
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.issue	2	en_US
pubs.publication-status	Published	en_US
pubs.volume	42	en_US

Abstract:

Conventional human action recognition algorithms cannot work well when the amount of training videos is insufficient. We solve this problem by proposing a transfer topic model (TTM), which utilizes information extracted from videos in the auxiliary domain to assist recognition tasks in the target domain. The TTM is well characterized by two aspects: 1) it uses the bag-of-words model trained from the auxiliary domain to represent videos in the target domain; and 2) it assumes each human action is a mixture of a set of topics and uses the topics learned from the auxiliary domain to regularize the topic estimation in the target domain, wherein the regularization is the summation of Kullback-Leibler divergences between topic pairs of the two domains. The utilization of the auxiliary domain knowledge improves the generalization ability of the learned topic model. Experiments on Weizmann and KTH human action databases suggest the effectiveness of the proposed TTM for cross-domain human action recognition. © 2006 IEEE.

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

http://hdl.handle.net/10453/22218