Statistical language models estimate the probability of a word occurring in a given context. The most common language models rely on a discrete enumeration of predictive contexts ...
John Blitzer, Kilian Q. Weinberger, Lawrence K. Sa...
In the context of knowledge-intensive work, making the relevant knowledge available to the people needing it for their work is a key issue. One approach is to capture such knowled...
A novel method unifying viewer and model centered approaches for representing structurally complex 3-D objects like human faces is presented. The uni ed 3D frequency-domain repres...
The suitability of polar representation for quantitative image processing tasks is investigated. The classical colour polar-based representations (HLS, HSV, etc.) lead to brightne...
We propose a mixture of multiple linear models, also known as hybrid linear model, for a sparse representation of an image. This is a generalization of the conventional KarhunenLo...