In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
Pattern recognition methods for complex structured objects such as handwritten characters often have to deal with vast search spaces. Developed techniques, despite significant adv...
Recently, `entry/exit' events of objects in the field-of-views of cameras were used to learn the topology of the camera network. The integration of object appearance was also...
Xiaotao Zou, Bir Bhanu, Bi Song, Amit K. Roy Chowd...
Abstract. In this paper we present di erent approaches to structuring covariance matrices within statistical classi ers. This is motivated by the fact that the use of full covarian...
This paper proposes a metric learning based approach for human activity recognition with two main objectives: (1) reject unfamiliar activities and (2) learn with few examples. We s...