Abstract. We tackle the problem of multi-class relational sequence learning using relevant patterns discovered from a set of labelled sequences. To deal with this problem, firstly...
Nicola Di Mauro, Teresa Maria Altomare Basile, Ste...
One Feature (1F) is a simple and intuitive pruning strategy that reduces considerably the amount of computations required by Nearest-Neighbor gesture classifiers while still pres...
We present analyses aimed at eliciting which specific aspects of discourse provide the strongest indication for text importance. In the context of content selection for single doc...
Abstract--An active shape model segmentation scheme is presented that is steered by optimal local features, contrary to normalized first order derivative profiles, as in the origin...
Bram van Ginneken, Alejandro F. Frangi, Joes Staal...
In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms us...