To assure dependable onboard evolution, we have developed a methodology called guarded software upgrading (GSU). In this paper, we focus on a low-cost approach to error containmen...
Ann T. Tai, Kam S. Tso, Leon Alkalai, Savio N. Cha...
We describe a learning-based method for low-level vision problems--estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, m...
Recently the problem of dimensionality reduction (or, subspace learning) has received a lot of interests in many fields of information processing, including data mining, informati...
Many object categories are better characterized by the shape of their contour than by local appearance properties like texture or color. Multi-local features are designed in order...
Oscar M. Danielsson, Stefan Carlsson, Josephine Su...
We propose a new approach for learning Bayesian classifiers from data. Although it relies on traditional Bayesian network (BN) learning algorithms, the effectiveness of our approa...