Learning over sets using boosted manifold principal angles (BoMPA)
Contribuinte(s) |
Clocksin, W F Fitzgibbon, A W Torr, P H S |
---|---|
Data(s) |
01/01/2005
|
Resumo |
In this paper we address the problem of classifying vector sets. We motivate and introduce a novel method based on comparisons between corresponding vector subspaces. In particular, there are two main areas of novelty: (i) we extend the concept of principal angles between linear subspaces to manifolds with arbitrary nonlinearities; (ii) it is demonstrated how boosting can be used for application-optimal principal angle fusion. The strengths of the proposed method are empirically demonstrated on the task of automatic face recognition (AFR), in which it is shown to outperform state-of-the-art methods in the literature. |
Identificador | |
Idioma(s) |
eng |
Publicador |
BMVA Press |
Relação |
http://dro.deakin.edu.au/eserv/DU:30058442/arandjelovic-learningoversets-2005.pdf http://doi.org/10.5244/C.19.58 |
Direitos |
2005, BMVA |
Tipo |
Conference Paper |