Bayesian Clustering of Optical Flow Fields

ICCV 2003 pp. 1086-1093

doi:10.1109/ICCV.2003.1238470 /iccv/2003/hoey2003iccv-bayesian/

Abstract

We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probabilistic fashion, which improves the estimation of the projections by incorporating uncertainties in the flows. We then cluster the projections using a mixture of feature-weighted Gaussians over optical flow fields. The resulting model extracts a concise probabilistic description of the major classes of optical flow present. The method is demonstrated on a video of a person's facial expressions.

ICCV Semantic Scholar

Cite

Text

Hoey and Little. "Bayesian Clustering of Optical Flow Fields." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238470

Markdown

[Hoey and Little. "Bayesian Clustering of Optical Flow Fields." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/hoey2003iccv-bayesian/) doi:10.1109/ICCV.2003.1238470

BibTeX

@inproceedings{hoey2003iccv-bayesian,
  title     = {{Bayesian Clustering of Optical Flow Fields}},
  author    = {Hoey, Jesse and Little, James J.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {1086-1093},
  doi       = {10.1109/ICCV.2003.1238470},
  url       = {https://mlanthology.org/iccv/2003/hoey2003iccv-bayesian/}
}