Expressing spatial information with iconic gestures is abundant in human communication and requires to transform a referent representation into resembling gestural form. This task ...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...
Approaches based on local features and descriptors are increasingly used for the task of object recognition due to their robustness with regard to occlusions and geometrical defor...
Background: Feature selection is a pattern recognition approach to choose important variables according to some criteria in order to distinguish or explain certain phenomena (i.e....
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...