AAAI Conference 2002 Conference Paper
Learning Temporal, Relational, Force-Dynamic Event Definitions from Video
- Alan Fern
- and Robert Givan
We present and evaluate a novel implemented approach for learning to recognize events in video. First, we introduce a sublanguage of event logic, called k-AMA, that is sufficiently expressive to represent visual events yet sufficiently restrictive to support learning. Second, we develop a specificto-general learning algorithm for learning event definitions in k-AMA. Finally, we apply this algorithm to the task of learning event definitions from video and show that it yields definitions that are competitive with hand-coded ones.