Abstract. The scale invariant property of an ensemble of natural images is examined which motivates a new early visual representation termed the higher order pyramid. The represent...
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...
Honglak Lee, Roger Grosse, Rajesh Ranganath, Andre...
This paper proposes two DSs to describe the visual information of an AV document. The first one, is devoted to still images. It describes the image visual appearance and its struc...
Philippe Salembier, Noel E. O'Connor, Paulo Correi...
Human visual recognition is based largely on shape, yet effectively using shapes in natural image retrieval is a challenging task. Most existing methods are based on the geometric...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...