Feature Seeding for Action Recognition

Pyry Matikainen, Rahul Sukthankar, and Martial Hebert
International Conference on Computer Vision 2011, December, 2011.


Download
  • Adobe portable document format (pdf) (2MB)
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.

Abstract
Progress in action recognition has been in large part due to advances in the features that drive learning-based methods. However, the relative sparsity of training data and the risk of overfitting have made it difficult to directly search for good features. In this paper we suggest using synthetic data to search for robust features that can more easily take advantage of limited data, rather than using the synthetic data directly as a substitute for real data. We demonstrate that the features discovered by our selection method, which we call seeding, improve performance on an action classification task on real data, even though the synthetic data from which the features are seeded differs significantly from the real data, both in terms of appearance and the set of action classes.

Notes

Text Reference
Pyry Matikainen, Rahul Sukthankar, and Martial Hebert, "Feature Seeding for Action Recognition," International Conference on Computer Vision 2011, December, 2011.

BibTeX Reference
@inproceedings{Matikainen_2011_6914,
   author = "Pyry Matikainen and Rahul Sukthankar and Martial Hebert",
   title = "Feature Seeding for Action Recognition",
   booktitle = "International Conference on Computer Vision 2011",
   month = "December",
   year = "2011",
}