The current research presents a system that learns to understand object names, spatial relation terms and event descriptions from observing narrated action sequences. The system e...
We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed ed...
The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use...
Vicarious Learning is learning from watching others learn. We believe that this is a powerful model for computer-based learning. Learning episodes can be captured and replayed to ...
This paper reports on a UK ESRC-funded project studying representations of practice, in video clips and voice annotations, for professional collaborative learning in distributed o...