In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
Several recently-proposed architectures for highperformance
object recognition are composed of two main
stages: a feature extraction stage that extracts locallyinvariant
feature...
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Rob Fergu...
Automatically understanding human actions from video sequences is a very challenging problem. This involves the extraction of relevant visual information from a video sequence, re...
This paper considers kernels invariant to translation, rotation and dilation. We show that no non-trivial positive deļ¬nite (p.d.) kernels exist which are radial and dilation inv...
In many applications, modelling techniques are necessary which take into account the inherent variability of given data. In this paper, we present an approach to model class speciļ...