In this paper we present an algorithm which uses adaptive selection of low-level features for main subject detection. The algorithm first computes low-level features such as contr...
The problem of automatic feature selection/weighting in kernel methods is examined. We work on a formulation that optimizes both the weights of features and the parameters of the ...
We present a nonparametric Bayesian model for multi-task learning, with a focus on feature selection in binary classification. The model jointly identifies groups of similar tas...
Building an accurate emerging pattern classifier with a highdimensional dataset is a challenging issue. The problem becomes even more difficult if the whole feature space is unava...
Kui Yu, Wei Ding 0003, Dan A. Simovici, Xindong Wu
This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences ar...