The Robotics Institute

Carnegie Mellon Robotics Institute

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

The popular bag-of-words paradigm for action recognition tasks is based on building histograms of quantized features, typically at the cost of discarding all information about relationships between them. However, although the benecial nature of including these relationships seems obvious, in practice nding good representations for feature relationships in video is dicult. We propose a simple and computationally efficient method for expressing pairwise relationships between quantized features that combines the power of discriminative representations with key aspects of Nave Bayes. We demonstrate how our technique can augment both appearance- and motion-based features, and that it significantly improves performance on both types of features.

Keywords

action recognition, spatial relationships

Notes

Text Reference

Pyry Matikainen, Martial Hebert, and Rahul Sukthankar, "Representing Pairwise Spatial and Temporal Relations for Action Recognition," European Conference on Computer Vision 2010 (ECCV 2010), September, 2010.

BibTeX Reference

@inproceedings{Matikainen_2010_6654,
   author = "Pyry Matikainen and Martial Hebert and Rahul Sukthankar",
   editor = "K. Daniilidis, P. Maragos, N. Paragios",
   title = "Representing Pairwise Spatial and Temporal Relations for Action Recognition",
   booktitle = "European Conference on Computer Vision 2010 (ECCV 2010)",
   month = "September",
   year = "2010",
}

The Robotics Institute

Menu