Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
Despite ubiquitous claims that optical character recognition (OCR) is a "solved problem," many categories of documents continue to break modern OCR software such as docu...
Although semi-supervised learning has been an active area of research, its use in deployed applications is still relatively rare because the methods are often difficult to impleme...
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...