Learning an Interest Operator from Human Eye Movements

Wolf Kienzle, Felix A. Wichmann, Bernhard Schölkopf, Matthias O. Franz

CVPRW 2006 pp. 24

doi:10.1109/CVPRW.2006.116 /cvprw/2006/kienzle2006cvprw-learning/

Abstract

We present an approach for designing interest operators that are based on human eye movement statistics. In contrast to existing methods which use hand-crafted saliency measures, we use machine learning methods to infer an interest operator directly from eye movement data. That way, the operator provides a measure of biologically plausible interestingness. We describe the data collection, training, and evaluation process, and show that our learned saliency measure significantly accounts for human eye movements. Furthermore, we illustrate connections to existing interest operators, and present a multi-scale interest point detector based on the learned function.

CVPRW Semantic Scholar

Cite

Text

Kienzle et al. "Learning an Interest Operator from Human Eye Movements." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006. doi:10.1109/CVPRW.2006.116

Markdown

[Kienzle et al. "Learning an Interest Operator from Human Eye Movements." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2006.](https://mlanthology.org/cvprw/2006/kienzle2006cvprw-learning/) doi:10.1109/CVPRW.2006.116

BibTeX

@inproceedings{kienzle2006cvprw-learning,
  title     = {{Learning an Interest Operator from Human Eye Movements}},
  author    = {Kienzle, Wolf and Wichmann, Felix A. and Schölkopf, Bernhard and Franz, Matthias O.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2006},
  pages     = {24},
  doi       = {10.1109/CVPRW.2006.116},
  url       = {https://mlanthology.org/cvprw/2006/kienzle2006cvprw-learning/}
}