Visual dictionaries have been successfully applied to "bags-of-points" image representations for generic object recognition. Usually the choice of low-level interest reg...
Semi-supervised clustering allows a user to specify available prior knowledge about the data to improve the clustering performance. A common way to express this information is in ...
The paper poses video-to-video face recognition as a dynamical system identification and classification problem. Video-to-video means that both gallery and probe consists of video...
Amit K. Roy Chowdhury, Gaurav Aggarwal, Rama Chell...
Recent empirical work has shown that combining predictors can lead to significant reduction in generalization error. The individual predictors (weak learners) can be very simple, ...
The maximum entropy principle is a cornerstone of FRAME (Filters, RAndom fields, and Maximum Entropy) model considered at times as a first-ever step towards a universal theory of ...
Georgy L. Gimel'farb, Luc J. Van Gool, Alexey Zale...