In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
—In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. ...
Machine learning methods that can use additional knowledge in their inference process are central to the development of integrative bioinformatics. Inclusion of background knowled...
Minca Mramor, Marko Toplak, Gregor Leban, Tomaz Cu...
Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connecte...
Abstract. The aim of this paper is to explore intrinsic geometric methods of recovering the three dimensional motion of a moving camera from a sequence of images. Generic similarit...