ERC Grant on Rich Structured Models …. We are hiring now !

The ERC project covers a range of topics from image matching to scene understanding. We are interested in students who want to explore theoretical concepts that can be applied to these application areas, such as combining CNN and CRFs; Deep, physics-based, learning, Large scale optimization, partial optimality, learning in probabilistic graphical models.

The brief, high-level, pitch is: Given a sequence of images the goal is to recover a rich, detailed representation of the 3D world, ranging from physical to semantic aspects. To achieve this we investigate new ways to combine feature learning, modelling, physical laws, and optimization in large-scale discrete-continuous-valued probabilistic graphical model.

Posted in Job offer.