Tracking groups of people is a highly informative task in surveillance, and it represents a still open and little explored issue. In this paper, we propose a brand new framework f...
Web 2.0 provided internet users with a dynamic medium, where information is updated continuously and anyone can participate. Though preliminary analysis exists, there is still lit...
Konstantinos N. Vavliakis, Andreas L. Symeonidis, ...
Conventional sentence compression methods employ a syntactic parser to compress a sentence without changing its meaning. However, the reference compressions made by humans do not ...
This paper proposes an approach to enhance dependency parsing in a language by using a translated treebank from another language. A simple statistical machine translation method, ...
This paper studies transliteration alignment, its evaluation metrics and applications. We propose a new evaluation metric, alignment entropy, grounded on the information theory, t...