We formulate a model for probability distributions on image spaces. We show that any distribution of images can be factored exactly into conditional distributions of feature vecto...
This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
This paper introduces new methods based on exponential families for modeling the correlations between words in text and speech. While previous work assumed the effects of word co-...
Colorhasbeen widelyused for handsegmentation. However, many approaches rely on predefined skin color models. It is very difficult to predefine a color model in a mobile applica...
Automatic image annotation is a promising solution to enable semantic image retrieval via keywords. In this paper, we propose a multi-level approach to annotate the semantics of n...