A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Class binarizations are effective methods for improving weak learners by decomposing multi-class problems into several two-class problems. This paper analyzes how these methods can...
This paper presents a method of automatically constructing information extraction patterns on predicate-argument structures (PASs) obtained by full parsing from a smaller training...
Machine Learning based on the Regularized Least Square (RLS) model requires one to solve a system of linear equations. Direct-solution methods exhibit predictable complexity and s...
Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...