This paper presents a statistical model for textures that uses a non-negative decomposition on a set of local atoms learned from an exemplar. This model is described by the varianc...
Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions re...
Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zi...
We present a novel cognitive agent architecture and demonstrate its effectiveness in the Sense and Respond Logistics (SRL) domain. Effective applications to support SRL must antic...
Kshanti A. Greene, David G. Cooper, Anna L. Buczak...
Detecting people in images is key for several important application domains in computer vision. This paper presents an in-depth experimental study on pedestrian classification; mul...
We consider the problem of image classification when more than one visual feature is available. In such cases, Bayes fusion offers an attractive solution by combining the result...