Matching points between multiple images of a scene is a vital component of many computer vision tasks. Point matching involves creating a succinct and discriminative descriptor fo...
Categorisation of objects into classes is currently supported by (at least) two ‘orthogonal’ methods. In logic-based approaches, classifications are defined through ontologi...
Mikhail Sheremet, Dmitry Tishkovsky, Frank Wolter,...
— This paper addresses recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such meas...
Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patri...
Background: Protein sequence alignments have become indispensable for virtually any evolutionary, structural or functional study involving proteins. Modern sequence search and com...
We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds i...