We present a method for learning a human understandable, executable model of an agent's behavior using observations of its interaction with the environment. By executable we ...
Andrew Guillory, Hai Nguyen, Tucker R. Balch, Char...
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 visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new...
Abstract. Although knowledge is a central topic for MKM there is little explicit discussion on what ‘knowledge’ might actually be. There are specific intuitions about form and...
— This paper addresses the problem of acquiring a hierarchically structured robotic skill in a nonstationary environment. This is achieved through a combination of learning primi...