It is widely conjectured that the excellent ROC performance of biological vision systems is due in large part to the exploitation of context at each of many levels in a part/whole...
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
In recent years, many principled probabilistic definitions for the determination of visual saliency have been proposed. Moreover, there has been increased focus on the role of con...
We develop latent Dirichlet allocation with WORDNET (LDAWN), an unsupervised probabilistic topic model that includes word sense as a hidden variable. We develop a probabilistic po...
Previous research on automatic image annotation has shown that accurate estimates of the class conditional densities in generative models have a positive effect in annotation perf...