In this paper, we formulate the stereo matching problem as a Markov network consisting of three coupled Markov random fields (MRF's). These three MRF's model a smooth fie...
In this paper we consider an object categorization system using local HMAX features. Two feature matching techniques are compared: the MAX technique, originally proposed in the HMA...
The estimation of a sparse vector in the linear model is a fundamental problem in signal processing, statistics, and compressive sensing. This paper establishes a lower bound on t...
In this paper we present a probabilistic and continuous framework for supervised image category modelling and matching as well as unsupervised clustering of image space into image...
: Suppose that independent U 0 1 weights are assigned to the d 2 n2 edges of the complete d-partite graph with n vertices in each of the d = maximal independent sets. Then the expe...