We perform knowledge discovery in software archives in order to detect refactorings on the level of classes and methods. Our REFVIS prototype finds these refactorings in CVS repo...
Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem...
Chris Mario Christoudias, Raquel Urtasun, Trevor D...
We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized corre...
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...
We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linkin...