ML Anthology

On Partial Least Squares in Head Pose Estimation: How to Simultaneously Deal with Misalignment

Murad Al Haj, Jordi Gonzàlez, Larry S. Davis
CVPR 2012 pp. 2602-2609
doi:10.1109/CVPR.2012.6247979 /cvpr/2012/haj2012cvpr-partial/

Abstract

Head pose estimation is a critical problem in many com-puter vision applications. These include human computer interaction, video surveillance, face and expression recog-nition. In most prior work on heads pose estimation, the positions of the faces on which the pose is to be estimated are specified manually. Therefore, the results are reported without studying the effect of misalignment. We propose a method based on partial least squares (PLS) regression to estimate pose and solve the alignment problem simultane-ously. The contributions of this paper are two-fold: 1) we show that the kernel version of PLS (kPLS) achieves better than state-of-the-art results on the estimation problem and 2) we develop a technique to reduce misalignment based on the learned PLS factors. 1.

PDF CVPR Semantic Scholar

Cite

Text

Al Haj et al. "On Partial Least Squares in Head Pose Estimation: How to Simultaneously Deal with Misalignment." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247979

Markdown

[Al Haj et al. "On Partial Least Squares in Head Pose Estimation: How to Simultaneously Deal with Misalignment." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/haj2012cvpr-partial/) doi:10.1109/CVPR.2012.6247979

BibTeX

@inproceedings{haj2012cvpr-partial,
  title     = {{On Partial Least Squares in Head Pose Estimation: How to Simultaneously Deal with Misalignment}},
  author    = {Al Haj, Murad and Gonzàlez, Jordi and Davis, Larry S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2602-2609},
  doi       = {10.1109/CVPR.2012.6247979},
  url       = {https://mlanthology.org/cvpr/2012/haj2012cvpr-partial/}
}