In this paper, we propose a generative model-based approach for audio-visual event classification. This approach is based on a new unsupervised learning method using an extended p...
Ming Li, Sanqing Hu, Shih-Hsi Liu, Sung Baang, Yu ...
A bilingual concept MRD is of significance for IE, MT, WSD and the like. However, it is reasonably difficult to build such a lexicon for there exist two ontologies, also, the evol...
We study visibly pushdown automata (VPA) models for expressing and evaluating queries, expressed using MSO formulas, on words with a nesting structure (like XML documents). We deļ...
We introduce perturbation kernels, a new class of similarity measure for information retrieval that casts word similarity in terms of multi-task learning. Perturbation kernels mode...
Abstract. We propose a theoretical framework for the optimal collaboration among researchers in a knowledge network in which researchers are not limited to a single discipline and ...