We attemped to improve recognition accuracy by reducing the inadequacies of the lexicon and language model. Specifically we address the following three problems: (1) the best size...
Richard M. Schwartz, Long Nguyen, Francis Kubala, ...
We present a versatile, fast and simple framework to generate animations of scanned human characters from input optical motion capture data. Our method is purely meshbased and req...
Edilson de Aguiar, Rhaleb Zayer, Christian Theobal...
This paper reports the results of a preliminary cross-evaluation experiment run in the framework of the European research project PF-Star1, with the double aim of evaluating the po...
Jonas Beskow, Loredana Cerrato, Piero Cosi, Erica ...
At current on-line shops, buyers almost independently enjoy shopping without anyone's help. However, there are many cases where they cooperate with people such as personal ad...
The World Wide Web provides a wealth of data that can be harnessed to help improve information retrieval and increase understanding of the relationships between different entities...