There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...
Honglak Lee, Roger Grosse, Rajesh Ranganath, Andre...
— In this paper we present a novel methodology for detection and tracking of facial features like eyes, nose and mouth in image sequences. The proposed methodology is intended to...
Maria Pateraki, Haris Baltzakis, Polychronis Konda...
Non-rigid object alignment is especially challenging when only a single appearance template is available and target and template images fail to match. Two sources of discrepancy b...
Numerical multilinear (tensor) algebra is a principled mathematical approach to disentangling and explicitly and parsimoniously representing the essential factors or modes of imag...
We consider the problem of estimating receiver coil sensitivity functions in parallel MRI. By exploiting the multichannel nature of the problem, where multiple acquisitions of the...