Spatial priors play crucial roles in many high-level vision tasks, e.g. scene understanding. Usually, learning spatial priors relies on training a structured output model. In this...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
Abstract. Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separa...