Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition

  title={Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition},
  author={David Minnen and Irfan A. Essa and Thad Starner},
Video-based recognition and prediction of a temporally extended activity can benefit from a detailed description of high-level expectations about the activity. Stochastic gr ammars allow for an efficient representation of such expectations and are well-suited for the specification of temporall y well-ordered activities. In this paper, we extend stochast ic grammars by adding event parameters, state checks, and sensitivity to an internal scene model. We present an implemented system that uses… CONTINUE READING
Highly Cited
This paper has 143 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 86 extracted citations

Semantic Representation and Recognition of Continued and Recursive Human Activities

International Journal of Computer Vision • 2008
View 4 Excerpts
Highly Influenced

On-Line Video Event Detection by Constraint Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2014
View 4 Excerpts
Highly Influenced

Mobile Intention Recognition

Springer New York • 2011
View 1 Excerpt
Highly Influenced

144 Citations

Citations per Year
Semantic Scholar estimates that this publication has 144 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…