This paper describes a method of detecting Japanese Katakana variants from a large corpus. Katakana words, which are mainly used as loanwords, cause problems with information retr...
Abstract. We introduce a view–point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on...
Abstract— Recently, several wireless sensor network studies demonstrated large discrepancies between experimentally observed communication properties and properties produced by w...
Alberto Cerpa, Jennifer L. Wong, Louane Kuang, Mio...
This paper provides a novel Web image clustering methodology based on their associated texts. In our approach, the semantics of Web images are firstly represented into vectors of t...
Although speech, derived from reading texts, and similar types of speech, e.g. that from reading newspapers or that from news broadcast, can be recognized with high accuracy, recog...