Many computer vision tasks may be expressed as the problem of learning a mapping between image space and a parameter space. For example, in human body pose estimation, recent rese...
Ramanan Navaratnam, Andrew W. Fitzgibbon, Roberto ...
Boosting is a general method for improving the accuracy of learning algorithms. We use boosting to construct improved privacy-preserving synopses of an input database. These are da...
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...
Reliable 3D tracking is still a difficult task. Most parametrized 3D deformable models rely on the accurate extraction of image features for updating their parameters, and are pro...
Christian Vogler, Zhiguo Li, Atul Kanaujia, Siome ...