The majority of existing tracking algorithms are based on the maximum a posteriori (MAP) solution of a probabilistic framework using a Hidden Markov Model, where the distribution ...
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
In this paper, we present a novel approach for extracting silhouettes by using a particular pattern that we call the random pattern. The volume intersection method reconstructs th...
Abstract. This paper identifies a new physical correlate of finger pressure that can be detected and measured visually in a wide variety of situations. When a human finger is press...
Joe Marshall, Tony P. Pridmore, Mike Pound, Steve ...
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. T...