In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a...
Supervised sequence-labeling systems in natural language processing often suffer from data sparsity because they use word types as features in their prediction tasks. Consequently...
Abstract. This paper shows that we can take advantage of information about the probabilities of the occurrences of events, when this information is available, to refine the classic...
Abstract. A fine-grained massively-parallel process-oriented model of platelets (potentially artificial) within a blood vessel is presented. This is a CSP inspired design, expres...
Abstract. Model-Integrated Computing is a proven technology for designing and implementing complex software systems. Making the designtime models available at run-time benefits the...