We address the problem of learning view-invariant 3D models of human motion from motion capture data, in order to recognize human actions from a monocular video sequence with arbi...
When a purely rotating camera observes a general scene, overlapping views are related by a parallax-free warp which can be estimated by direct image alignment methods that iterate ...
Subcellular localization is a key functional characteristic of proteins. An automatic, reliable and efficient prediction system for protein subcellular localization is needed for ...
An important problem in biological data analysis is to predict the family of a newly discovered sequence like a protein or DNA sequence, using the collection of available sequence...
Background: Many current gene prediction methods use only one model to represent proteincoding regions in a genome, and so are less likely to predict the location of genes that ha...
Shaun Mahony, James O. McInerney, Terry J. Smith, ...