We show in this paper that the influential algorithm of iterative belief propagation can be understood in terms of exact inference on a polytree, which results from deleting enoug...
Creating a robust image classification system depends on having enough data with which one can adequately train and validate the model. If there is not enough available data, this...
We have created LADDER, the first language to describe how sketched diagrams in a domain are drawn, displayed, and edited. The difficulty in creating such a language is choosing...
When the amount of information in visualization becomes large enough, users can not perceive all elements at the same time. This problem can be solved by removing parts of the inf...
: The World Wide Web is in constant renovation, with new technologies emerging every day. Most of these technologies are still incipient, and there are few de facto standards for t...