This paper addresses the challenge of recognizing behavior of groups of individuals in unconstraint surveillance environments. As opposed to approaches that rely on agglomerative ...
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, r...
In this paper, we model the pair-wise similarities of a set of documents as a weighted network with a single cutoff parameter. Such a network can be thought of an ensemble of unwe...
Abstract. In recent years, the World Wide Web (WWW) has transformed to a gigantic social network where people interact and collaborate in diverse online communities. By using Web 2...
Abstract. The prediction of diagnosis codes is typically based on freetext entries in clinical documents. Previous attempts to tackle this problem range from strictly rule-based sy...