Abstract. This paper presents a novel technique for learning the underlying structure that links visual observations with semantics. The technique, inspired by a text-retrieval tec...
Jonathon S. Hare, Paul H. Lewis, Peter G. B. Enser...
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
Abstract. The need of the current Natural Language Processing applications to identify text segments that express the same meaning in different ways, evolved into the identificatio...
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
Representing documents by vectors that are independent of language enhances machine translation and multilingual text categorization. We use discriminative training to create a pr...