1, Event Parsing by AND-OR grammar with Goal and Intent Inference

We present an event parsing algorithm based on Stochastic Context Sensitive Grammar (SCSG) for understanding events, inferring the goal of agents, and predicting their plausible intended actions.

2, Learning event AND-OR grammar from daily video

We study the problem of automatically learning event AND-OR grammar from videos in a controlled environment, e.g. an office where students conduct daily activities. We learn the event gammar under the information projection and minimum description length principles in a coherent probabilistic framework, without manual supervision about what events happen and when they happen.