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...
"Bag of words" models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are mo...
This paper deals with estimation of dense optical flow
and ego-motion in a generalized imaging system by exploiting
probabilistic linear subspace constraints on the flow.
We dea...
Richard Roberts (Georgia Institute of Technology),...
This paper introduces an approach for handling complex labelling problems driven by local constraints. The purpose is illustrated by two applications: detection of the road networ...
Computer visualization and networking have advanced dramatically over the last few years, partially driven by the exploding video game market. 3D hardware acceleration has reached...