We introduce a framework for actively learning visual categories from a mixture of weakly and strongly labeled image examples. We propose to allow the categorylearner to strategic...
Interactive motion segmentation is an important task for scene understanding and analysis. Despite recent progress state-of-theart approaches still have difficulties in adapting to...
Claudia Nieuwenhuis, Benjamin Berkels, Martin Rump...
An adequate understanding of climate variability and the eventual prediction of climate change are among the most urgent and far-reaching efforts of the scientific community.. Mea...
Ramprasad Balasubramanian, Vishal Sood, Bin John, ...
Fitting statistical models is a widely employed technique for the segmentation of medical images. While this approach gives impressive results for simple structures, shape models a...
Many current medical image analysis problems involve learning thousands or even millions of model parameters from extremely few samples. Employing sparse models provides an effecti...