Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
This paper describes a new bipartite formulation for word-document co-clustering such that hyperclique patterns, strongly affiliated documents in this case, are guaranteed not to ...
Tianming Hu, Chao Qu, Chew Lim Tan, Sam Yuan Sung,...
In this article, we focus our efforts (i) on the study of how to automatically extract and exploit visual concepts and (ii) on fast visual diversity. First, in the Visual Concept D...
Sabrina Tollari, Marcin Detyniecki, Ali Fakeri-Tab...
Likelihood-based marginal regression modelling for repeated, or otherwise clustered, categorical responses is computationally demanding. This is because the number of measures nee...
Abstract. Cast indexing is a very important application for contentbased video browsing and retrieval, since the characters in feature-length films and TV series are always the ma...
Wei Fan, Tao Wang, Jean-Yves Bouguet, Wei Hu, Yimi...