Linear subspace methods that provide sufficient reconstruction of the data, such as PCA, offer an efficient way of dealing with missing pixels, outliers, and occlusions that often ...
Abstract. Discriminative and generative methods provide two distinct approaches to machine learning classification. One advantage of generative approaches is that they naturally mo...
We propose a highly efficient framework for penalized likelihood kernel methods applied to multiclass models with a large, structured set of classes. As opposed to many previous a...
Hybrid generative-discriminative techniques and, in particular, generative score-space classification methods have proven to be valuable approaches in tackling difficult object or...
Alessandro Perina, Marco Cristani, Umberto Castell...
Current research on shape based classification has been generally aimed at utilising various visual features. Previous research has shown that the existing knowledge in a specific...