An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...
Fusional languages have rich inflection. As a consequence, tagsets capturing their morphological features are necessarily large. A natural way to make a tagset manageable is to us...
Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared ...
This paper addresses the design issue of System-onelevating the design abstraction levels, through a model-driven approach. It considers the standard Marte profile, which is dedic...
In this paper, we propose a novel system working on the Web for personal media sharing and authoring. Three primary technologies enable this end-to-end system, including scalable ...