This paper proposes a novel approach to constructing a hierarchical representation of visual input that aims to enable recognition and detection of a large number of object catego...
Anticipation and prediction have been identified as key functions of many brain areas facilitating recognition, perception, and planning. In this chapter we present a hierarchical ...
: The SIFT algorithm (Scale Invariant Feature Transform) proposed by Lowe [1] is an approach for extracting distinctive invariant features from images. It has been successfully app...
Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. Such descriptors explicitly code local appearance and h...
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...