In this paper, we present a connectionist approach for detecting and precisely localizing semi-frontal human faces in complex images, making no assumption about the content or the...
This paper introduces a novel method for generating an intermediate view of soccer scene taken by multiple video cameras. In the proposed method, soccer scene is classified into d...
The MPEG-7 standard is emerging as both a general framework for content description and a collection of specific, agreed-upon content descriptors. We have developed a neural, self...
In this paper, we propose a new context-sensitive Bayesian learning algorithm. By modeling the distributions of data locations by a mixture of Gaussians, the new algorithm can uti...
The use of higher order autocorrelations as features for pattern classification has been usually restricted to second or third orders due to high computational costs. Since the au...