—In an attempt to increase the performance/cost ratio, large compute clusters are becoming heterogeneous at multiple levels: from asymmetric processors, to different system archi...
We introduce a fibre tract segmentation algorithm based on the geometric coherence of fibre orientations as indicated by a streamline flow model. The inference of local flow approx...
Peter Savadjiev, Jennifer S. W. Campbell, G. Bru...
This paper introduces a semi-supervised distance metric learning algorithm which uses pair-wise equivalence (similarity and dissimilarity) constraints to improve the original dist...
Abstract. We propose two differential geometric representations of planar shapes using: (i) direction functions and (ii) curvature functions, of their boundaries. Under either rep...
Anuj Srivastava, Washington Mio, Eric Klassen, Sha...
Unsupervised learning requires a grouping step that defines which data belong together. A natural way of grouping in images is the segmentation of objects or parts of objects. Whi...