In this paper, we propose the use of the Maximum Entropy approach for the task of automatic image annotation. Given labeled training data, Maximum Entropy is a statistical techniqu...
While discriminative training (e.g., CRF, structural SVM) holds much promise for machine translation, image segmentation, and clustering, the complex inference these applications ...
This talk has two parts explaining the significance of Rough sets in granular computing in terms of rough set rules and in uncertainty handling in terms of lower and upper approxi...
An important topic in face recognition as well as in video coding or multi-modal human machine interfaces is the automatic localization of faces or headand-shoulder regions in vis...
Recent work has exploited boundedness of data in the unsupervised learning of new types of generative model. For nonnegative data it was recently shown that the maximum-entropy ge...