Please use this identifier to cite or link to this item: https://doi.org/10.1109/TIP.2008.2010210
DC FieldValue
dc.titleMode-kn factor analysis for image ensembles
dc.contributor.authorYan, S.
dc.contributor.authorWang, H.
dc.contributor.authorTu, J.
dc.contributor.authorTang, X.
dc.contributor.authorHuang, T.S.
dc.date.accessioned2014-10-07T04:32:33Z
dc.date.available2014-10-07T04:32:33Z
dc.date.issued2009
dc.identifier.citationYan, S., Wang, H., Tu, J., Tang, X., Huang, T.S. (2009). Mode-kn factor analysis for image ensembles. IEEE Transactions on Image Processing 18 (3) : 670-676. ScholarBank@NUS Repository. https://doi.org/10.1109/TIP.2008.2010210
dc.identifier.issn10577149
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/82707
dc.description.abstractIn this corespondence, we study the extra-factor estimation problem with the assumption that the training image ensemble is expressed as an nth-order tensor with the nth-dimension characterizing all features for an image and other dimensions for different extra factors, such as illuminations, poses, and identities. To overcome the local minimum issue of conventional algorithms designed for this problem, we present a novel statistical learning framework called mode-kn Factor Analysis for obtaining a closed-form solution to estimating the extra factors of any test image. In the learning stage, for the kth (k ≠ n) dimension of the data tensor, the mode-kn patterns are constructed by concatenating the feature dimension and the kth extra-factor dimension, and then a mode-kn factor analysis model is learnt based on the mode-kn patterns unfolded from the original data tensor. In the inference stage, for a test image, the mode classification of the kth dimension is performed within a probabilistic framework. The advantages of mode-kn factor analysis over conventional tensor analysis algorithms are twofold: 1) a closed-form solution, instead of iterative sub-optimal solution as conventionally, is derived for estimating the extra-factor mode of any test image; and 2) the classification capability is enhanced by interacting with the process of synthesizing data of all other modes in the kth dimension. Experiments on the Pointing'04 and CMU PIE databases for pose and illumination estimation both validate the superiority of the proposed algorithm over conventional algorithms for extra-factor estimation. © 2009 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/TIP.2008.2010210
dc.sourceScopus
dc.subjectFactor analysis
dc.subjectMultilinear analysis
dc.subjectPose estimation
dc.subjectTensor representation
dc.typeArticle
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/TIP.2008.2010210
dc.description.sourcetitleIEEE Transactions on Image Processing
dc.description.volume18
dc.description.issue3
dc.description.page670-676
dc.description.codenIIPRE
dc.identifier.isiut000263604700018
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

5
checked on May 28, 2020

WEB OF SCIENCETM
Citations

3
checked on May 19, 2020

Page view(s)

58
checked on May 31, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.