Abstract. Object localization and tracking are key issues in the analysis of scenes for video surveillance or scene understanding applications. This paper presents a contribution t...
The formalism of probabilistic graphical models provides a unifying framework for capturing complex dependencies among random variables, and building large-scale multivariate stat...
Traditional machine learning algorithms assume that data are exact or precise. However, this assumption may not hold in some situations because of data uncertainty arising from mea...
Jiangtao Ren, Sau Dan Lee, Xianlu Chen, Ben Kao, R...
Crowdsourcing is an effective tool to solve hard tasks. By bringing 100,000s of people to work on simple tasks that only humans can do, we can go far beyond traditional models of ...
– Better understanding the document logical components is crucial to many applications, e.g., document classification or data integration. As the development of digital libraries...