Standard hidden Markov models (HMM's) have been studied extensively in the last two decades. It is well known that these models assume state conditional independence of the ob...
Abstract--The main contribution of this work is a new paradigm for image representation and image compression. We describe a new multilayered representation technique for images. A...
Abstract. In this paper we present DOMMLite - an extensible domainspecific language (DSL) for static structure definition of databaseoriented applications. The model-driven enginee...
Igor Dejanovic, Gordana Milosavljevic, Branko Peri...
Deep-layer machine learning architectures continue to emerge as a promising biologically-inspired framework for achieving scalable perception in artificial agents. State inference ...
In this paper we present a method for learning a curve model for detection and segmentation by closely integrating a hierarchical curve representation using generative and discrim...
Adrian Barbu, Vassilis Athitsos, Bogdan Georgescu,...