A modified version for semi-supervised learning algorithm with local and global consistency was proposed in this paper. The new method adds the label information, and adopts the g...
Abstract. We propose a learning method which introduces explicit knowledge to the object correspondence problem. Our approach uses an a priori learning set to compute a dense corre...
This paper introduces three new contributions to the problems of image classification and image search. First, we propose a new image patch quantization algorithm. Other competitiv...
Currently national digital library of educational resources and services (DLE) for primary and secondary education is under implementation in Lithuania. The article aims to analyse...
We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
Leonid Karlinsky, Michael Dinerstein, Dan Levi, Sh...