In this paper, we propose a novel approach for automatic generation of visualizations from domain-specific data available on the web. We describe a general system pipeline that co...
: This paper presents an approach to model ontologies for the e-Government domain as a basis for an integrated e-Government environment. Over the last couple of years the applicati...
The ubiquitous computing vision is to make knowledge and services easily available in our everyday environments. A wide range of devices, applications and services can be intercon...
This paper presents our approaches and results of the four TRECVID 2008 tasks we participated in: high-level feature extraction, automatic video search, video copy detection, and ...
We present a novel approach to weakly supervised semantic class learning from the web, using a single powerful hyponym pattern combined with graph structures, which capture two pr...