Image-based representations of an object profit from known geometry. The more accurate this geometry is known, the better corresponding pixels in the different images can be align...
Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Standardized middleware is used to build large distributed real-time and enterprise (DRE) systems. These middleware are highly flexible and support a large number of features sin...
In typical classification tasks, we seek a function which assigns a label to a single object. Kernel-based approaches, such as support vector machines (SVMs), which maximize the ...
Software re-engineering is one of the solutions advocated for the problems that are encountered during maintenance. The three major phases of a re-engineering process are (i) reve...