This paper presents a new technique which incrementally builds a hierarchical discriminant regression (IHDR) tree for generation of motion based robot reactions. The robot learned...
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objec...
Aria Haghighi, John Blitzer, John DeNero, Dan Klei...
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. ...
Abstract. Humans have the remarkable ability to generalize from binocular to monocular figure-ground segmentation of complex scenes. This is clearly evident anytime we look at a p...
Brian Mingus, Trent Kriete, Seth A. Herd, Dean Wya...