One of the most fundamental problems automatic parallelization tools are confronted with is to find an optimal domain decomposition for a given application. For regular domain prob...
While recognition of most facial variations, such as identity, expression and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast ...
In this paper, a novel automatic image annotation system is proposed, which integrates two sets of support vector machines (SVMs), namely the multiple instance learning (MIL)-base...
Many search problems contain large amounts of redundancy in the search. In this paper we examine how to automatically exploit remaining subproblem equivalence, which arises when tw...
Geoffrey Chu, Maria Garcia de la Banda, Peter J. S...
This thesis aims to analyze, model, and develop a framework for next-generation multimedia authoring tools targeted to end-users. In particular, I concentrate on the combination o...