Action Recognition by Learning Mid-Level Motion Features

Abstract

This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches or large-scale features describing the entire human figure. We develop a method constructing mid-level motion features which are built from low-level optical flow information. These features are focused on local regions of the image sequence and are created using a variant of AdaBoost. These features are tuned to discriminate between different classes of action, and are efficient to compute at run-time. A battery of classifiers based on these mid-level features is created and used to classify input sequences. State-of-the-art results are presented on a variety of standard datasets.

Cite

Text

Fathi and Mori. "Action Recognition by Learning Mid-Level Motion Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587735

Markdown

[Fathi and Mori. "Action Recognition by Learning Mid-Level Motion Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/fathi2008cvpr-action/) doi:10.1109/CVPR.2008.4587735

BibTeX

@inproceedings{fathi2008cvpr-action,
  title     = {{Action Recognition by Learning Mid-Level Motion Features}},
  author    = {Fathi, Alireza and Mori, Greg},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587735},
  url       = {https://mlanthology.org/cvpr/2008/fathi2008cvpr-action/}
}