Carnegie Mellon University
Browse

Feature Seeding for Action Recognition

Download (1.18 MB)
journal contribution
posted on 2011-11-01, 00:00 authored by Pyry Matikainen, Rahul Sukthankar, Martial Hebert

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.

History

Date

2011-11-01

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC