We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...
Tagged Magnetic Resonance Imaging (tMRI) is a non-invasive way of tracking the in-vivo myocardial motion during cardiac cycles. Tags are material points which deform along the myo...
We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic...
We describe an automatic method for building optimal 3D statistical shape models from sets of training shapes. Although shape models show considerable promise as a basis for segmen...
Rhodri H. Davies, Carole J. Twining, Timothy F. Co...
A major challenge for face recognition algorithms lies in the variance faces undergo while changing pose. This problem is typically addressed by building view dependent models bas...