We investigate to what extent combinations of features can improve classification performance on a large dataset of similar classes. To this end we introduce a 103 class flower da...
Abstract. In this paper, we propose a new method for image classification, in which matrix based kernel features are designed to capture the multiple similarities between images in...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...
Class posterior distributions have recently been used quite successfully in Automatic Speech Recognition (ASR), either for frame or phone level classification or as acoustic featu...
This paper investigates the potential information provided to the user by the uncertainty measures applied to the possibility distributions associated with the spatial units of an ...