Neurocomputing   

Special Issue on   

Subspace Learning    Subspace  learning,  a  typical  neurocomputing  technique,  sheds  light  on  various  tasks  from  computer  vision  to  data  mining.  A  subspace  learning  algorithm  projects  the  original  high  dimensional feature space to a low dimensional subspace, wherein specific statistical properties  can  be  well  preserved.  For  example,  Fisher’s  linear  discriminant  analysis  preserves  the  classification  structure  in  the  low  dimensional  projected  subspace  by  assuming  samples  are  drawn from homoscedastic unimodal Gaussians.    The  past  years  witnessed  very  significant  contributions  of  subspace  learning  for  various  applications,  e.g.,  face  identification  and  authentication,  human  gait  analysis,  video  tracking,  document  classification,  scene  understanding,  object  categorization,  and  multimedia  information retrieval. Subspace learning has been furthered from relevant research fields, e.g.,  nonparametric  Bayesian  analysis,  manifold  learning,  spectral  analysis,  kernel  machine,  tensor  machine,  and  incremental  learning.  As  a  consequence,  subspace  learning  is  a  never‐ending  resilience field and attracts growing efforts from different fields.    Elsevier  Neurocomputing  hunts  for  original  research  results  for  a  Special  Issue  on  Subspace  Learning.  The  goals  of  this  special  issue  are  twofold:  1)  developing  subspace  learning  algorithms to target specific applications and 2) defining applications, which can be cleared up  by subspace learning algorithms.    Manuscripts are solicited to address a wide range of topics in subspace learning, but not limit  to the following:    - Extensions of Fisher’s linear discriminant analysis and other traditional subspace learning  algorithms, e.g., principal component analysis.  - Spectral analysis  - Probabilistic graphical models  - Manifold learning  - Kernel machines and tensor machines  - Supervised, semi‐supervised and unsupervised subspace analysis  - Sparse analysis  - Subspace learning for biometrics, e.g., face.  - Subspace learning for multimedia information retrieval, e.g., relevance feedback and active  sample selection.  - Subspace learning for video surveillance, e.g., video tracking, motion analysis and  background modeling.   

Manuscripts (6‐15 pages in the Neurocomputing publishing format) should be submitted via  the Electronic Editorial System, Elsevier: http://ees.elsevier.com/neucom/   Important: when submitting your manuscript, at the step of “Selecting an Article Type is  Required for Submission”, please indicate: “Special Issue: Subspace Learning”      Important Dates    Manuscript submission:   10 May 2009  Preliminary results:    10 July 2009  Revised version:    10 August 2009  Notification:      10 October 2009  Final manuscripts due:    10 November 2009  Anticipated publication:    Spring 2010      Guest editors:    Xuelong Li  Birkbeck College, University of London [email protected] Dacheng Tao  Nanyang Technological University  [email protected]  

Neurocomputing

computer vision to data mining. A subspace learning ... applications, e.g., face identification and authentication, human gait analysis, video tracking, document ...

157KB Sizes 5 Downloads 141 Views

Recommend Documents

2013-Neurocomputing-OPSRC.pdf
the linear algorithms Principal Component Analysis (PCA) [3] and. Linear Discriminative Analysis (LDA) [4] had been the two most. popular methods due to their ...

2013-Neurocomputing-OPSRC.pdf
There was a problem loading this page. 2013-Neurocomputing-OPSRC.pdf. 2013-Neurocomputing-OPSRC.pdf. Open. Extract. Open with. Sign In. Main menu.

Neurocomputing aspects in modelling cursive ...
OOOl-6918/93/$06.00 0 1993 - Elsevier Science Publishers B.V. All rights reserved ..... tion (over the field of body-icons) of the degree of compliance with the different constraints that ... 223. X. Fig. 2. Cortical map of a 2 dof arm after training

Neurocomputing aspects in modelling cursive ... - ScienceDirect
robust and coherent maps of the different motor spaces) with relaxation dynamics (for run-time incorporation of task constraints) and non-linear integration (for a ...