We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this ...
We present a new approach to large-scale graph mining based on so-called backbone refinement classes. The method efficiently mines tree-shaped subgraph descriptors under minimum f...
Dynamic compilers can optimize application code specifically for observed code behavior. Such behavior does not have to be stable across the entire program execution to be bene...
Christian Wimmer, Marcelo Silva Cintra, Michael Be...
The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously Ncat = 104 -...
Background: Development of robust and efficient methods for analyzing and interpreting high dimension gene expression profiles continues to be a focus in computational biology. Th...