We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
When data collection is costly and/or takes a significant amount of time, an early prediction of the classifier performance is extremely important for the design of the data minin...
An activity consists of an actor performing a series of actions in a pre-defined temporal order. An action is an individual atomic unit of an activity. Different instances of the ...
In this paper we describe a new approach for learning dialog act processing. In this approach we integrate a symbolic semantic segmentation parse,: with a learning dialog act netw...
Based on our experience using active learning methods to teach object-oriented software design we propose a game-based approach to take the classroom experience into a virtual envi...