We present two theses in this paper: First, performance of most existing face recognition algorithms improves if instead of the whole image, smaller patches are individually class...
Ritwik Kumar, Arunava Banerjee, CISE, Univ, Baba V...
This paper describes a new method for creating visually realistic moving facial image sequences that retain an actor's personality (individuality, expression and characterist...
We describe a generative model of the relationship between two images. The model is deļ¬ned as a factored threeway Boltzmann machine, in which hidden variables collaborate to deļ...
Joshua Susskind, Roland Memisevic, Geoffrey Hinton...
This paper proposes a new approach to 3D reconstruction of piecewise planar objects based on two image regularities, connectivity and perspective symmetry. First, we formulate the...
In this paper we propose a novel method for demographic classification and present an image retrieval system that can retrieve facial images by demographic information that includ...