We seek a framework that addresses localization, detection and recognition of man-made objects in natural-scene images in a unified manner. We propose to model artificial structur...
State-of-the-art object retrieval systems are mostly based on the bag-of-visual-words representation which encodes local appearance information of an image in a feature vector. A ...
The use of Support Vector Machines (SVMs) to represent the performance space of analog circuits is explored. In abstract terms, an analog circuit maps a set of input design parame...
Fernando De Bernardinis, Michael I. Jordan, Albert...
A general-purpose augmented reality apparatus was developed. The system uses rapidly scanned lasers to display information directly onto the patient using the patient as a ``proje...
Neil D. Glossop, Chris Wedlake, John Moore, Terry ...
We propose an unbounded-depth, hierarchical, Bayesian nonparametric model for discrete sequence data. This model can be estimated from a single training sequence, yet shares stati...