We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents. The dialogue strategies were learnt in a simulated environment a...
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. T...
Designing complex multi-tier applications that must meet strict performance requirements is a challenging software engineering problem. Ideally, the application architect could de...
This paper presents a fully automatic framework for the restoration of double-sided historical manuscripts which are impaired by ink bleed-through distortions. First, the recto si...
Finite domain propagation solving, the basis of constraint programming (CP) solvers, allows building very high-level models of problems, and using highly specific inference encapsu...