Robust dimensionality reduction for human action recognition

Concha, OP; Da Xu, RY; Piccardi, M

Robust dimensionality reduction for human action recognition

Concha, OP Da Xu, RY Piccardi, M

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings - 2010 Digital Image Computing: Techniques and Applications, DICTA 2010, 2010, pp. 349 - 356
Issue Date:: 2010-12-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (163.66 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Concha, OP	en_US
dc.contributor.author	Da Xu, RY	en_US
dc.contributor.author	Piccardi, M https://orcid.org/0000-0001-9250-6604	en_US
dc.date.issued	2010-12-01	en_US
dc.identifier.citation	Proceedings - 2010 Digital Image Computing: Techniques and Applications, DICTA 2010, 2010, pp. 349 - 356	en_US
dc.identifier.isbn	9780769542713	en_US
dc.identifier.uri	http://hdl.handle.net/10453/16577
dc.description.abstract	Human action recognition can be approached by combining an action-discriminative feature set with a classifier. However, the dimensionality of typical feature sets joint with that of the time dimension often leads to a curse-of-dimensionality situation. Moreover, the measurement of the feature set is subject to sometime severe errors. This paper presents an approach to human action recognition based on robust dimensionality reduction. The observation probabilities of hidden Markov models (HMM) are modelled by mixtures of probabilistic principal components analyzers and mixtures of t-distribution sub-spaces, and compared with conventional Gaussian mixture models. Experimental results on two datasets show that dimensionality reduction helps improve the classification accuracy and that the heavier-tailed t-distribution can help reduce the impact of outliers generated by segmentation errors. © 2010 Crown Copyright.	en_US
dc.relation.ispartof	Proceedings - 2010 Digital Image Computing: Techniques and Applications, DICTA 2010	en_US
dc.relation.isbasedon	10.1109/DICTA.2010.66	en_US
dc.title	Robust dimensionality reduction for human action recognition	en_US
dc.type	Conference Proceeding
utslib.for	120304 Digital and Interaction Design	en_US
dc.location.activity	Sydney, Australia	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 Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Strength - INEXT - Innovation in IT Services and Applications
utslib.copyright.status	open_access
pubs.publication-status	Published	en_US

Abstract:

Human action recognition can be approached by combining an action-discriminative feature set with a classifier. However, the dimensionality of typical feature sets joint with that of the time dimension often leads to a curse-of-dimensionality situation. Moreover, the measurement of the feature set is subject to sometime severe errors. This paper presents an approach to human action recognition based on robust dimensionality reduction. The observation probabilities of hidden Markov models (HMM) are modelled by mixtures of probabilistic principal components analyzers and mixtures of t-distribution sub-spaces, and compared with conventional Gaussian mixture models. Experimental results on two datasets show that dimensionality reduction helps improve the classification accuracy and that the heavier-tailed t-distribution can help reduce the impact of outliers generated by segmentation errors. © 2010 Crown Copyright.

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

http://hdl.handle.net/10453/16577