To automatically register foreground target in cluttered images, we present a novel hierarchical graph representation and a stochastic computing strategy in Bayesian framework. Th...
Xiaobai Liu, Liang Lin, Hongwei Li, Hai Jin, Wenbi...
In this paper we introduce a novel method to address minimization of static and dynamic MRFs. Our approach is based on principles from linear programming and, in particular, on pr...
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 `...
In this paper we introduce the MeanNN approach for estimation of main information theoretic measures such as differential entropy, mutual information and divergence. As opposed to...
Protein structure comparison is important for elucidation of evolutionary relationships, function and functionally important amino acid residues. We propose Geometric Invariant bas...