ML Anthology

Action Spotting Exploiting the Frequency Domain

Irene Kotsia, Vasileios Argyriou
CVPRW 2011 pp. 43-48
doi:10.1109/CVPRW.2011.5981749 /cvprw/2011/kotsia2011cvprw-action/

Abstract

In this paper we present a novel method for action spotting in a video sequence, that employs the 3D Fourier transform in order to define a 3D gradient correlation function operating at the frequency domain. In that way we achieve invariance to spatiotemporal variations and also to frame reordering. One of the most attractive features of the proposed scheme is it's high degree of computational efficiency and the fact that it can be implemented by fast transformation algorithms in the frequency domain. Experiments conducted to a publicly available database demonstrated the superiority of the proposed method in terms of more accurate estimations and significantly lower computational complexity.

CVPRW Semantic Scholar

Cite

Text

Kotsia and Argyriou. "Action Spotting Exploiting the Frequency Domain." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011. doi:10.1109/CVPRW.2011.5981749

Markdown

[Kotsia and Argyriou. "Action Spotting Exploiting the Frequency Domain." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011.](https://mlanthology.org/cvprw/2011/kotsia2011cvprw-action/) doi:10.1109/CVPRW.2011.5981749

BibTeX

@inproceedings{kotsia2011cvprw-action,
  title     = {{Action Spotting Exploiting the Frequency Domain}},
  author    = {Kotsia, Irene and Argyriou, Vasileios},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2011},
  pages     = {43-48},
  doi       = {10.1109/CVPRW.2011.5981749},
  url       = {https://mlanthology.org/cvprw/2011/kotsia2011cvprw-action/}
}