We consider "swept regions" and "swept hypersurfaces"B in Rn+1 (and especially R3) which are a disjoint union of subspaces t = t or Bt = Bt obtained from a va...
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...
Time-varying spatial patterns are common, but few computational tools exist for discovering and tracking multiple, sometimes overlapping, spatial structures of targets. We propose...
Noisy probabilistic relational rules are a promising world model representation for several reasons. They are compact and generalize over world instantiations. They are usually in...
This paper presents a general approach to modeling VBR (variable bit rate) compressed full-motion video. The salient feature of such video is the existence of scenes. Scene struct...