Unsupervised Learning of Human Activity Grammars from Noisy Input Sequences

July 2008

Unsupervised Learning of Human Activity Grammars from Noisy Input Sequences

Authors:

Kris M. Kitani, Yoichi Sato, and Akihiro Sugimoto

Abstract:

Context-Free Grammars have been shown to be useful for applications beyond natural language analysis, specifically vision-based human activity analysis. However, vision-based symbol strings differ from natural language strings, in that a string of symbols produced by video can contain noise symbols, making grammatical inference very difficult. To obtain reliable results from grammatical inference, it is necessary to identify these noise symbols. We propose a new technique for identifying the best subset of terminal symbols to acquire the best activity grammar. Our approach uses the Minimum Description Length principle, to evaluate the trade-offs between model complexity and data fit to quantify the difference between the results of each terminal subset. The evaluation results are then used to identify of a class of candidate terminal subsets and grammars that remove the noise and enable the discovery of the basic structure of an activity. In this paper, we present the validity of our proposed method based on experiments with artificial and real data.
@article{Kitani-2008-109772,
author = {Kris M. Kitani And Yoichi Sato And Akihiro Sugimoto},
title = {Unsupervised Learning of Human Activity Grammars from Noisy Input Sequences},
journal = {Proceedings of IPSJ Transactions on Computer Vision and Image Media},
year = {2008},
month = {July},
volume = {1},
number = {2},
pages = {86 - 99},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.