ML Anthology

Nonparametric Bottom-up Saliency Detection by Self-Resemblance

Hae Jong Seo, Peyman Milanfar
CVPRW 2009 pp. 45-52
doi:10.1109/CVPRW.2009.5204207 /cvprw/2009/seo2009cvprw-nonparametric/

Abstract

We present a novel bottom-up saliency detection algorithm. Our method computes so-called local regression kernels (i.e., local features) from the given image, which measure the likeness of a pixel to its surroundings. Visual saliency is then computed using the said "self-resemblance" measure. The framework results in a saliency map where each pixel indicates the statistical likelihood of saliency of a feature matrix given its surrounding feature matrices. As a similarity measure, matrix cosine similarity (a generalization of cosine similarity) is employed. State of the art performance is demonstrated on commonly used human eye fixation data [3] and some psychological patterns.

PDF CVPRW Semantic Scholar

Cite

Text

Seo and Milanfar. "Nonparametric Bottom-up Saliency Detection by Self-Resemblance." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009. doi:10.1109/CVPRW.2009.5204207

Markdown

[Seo and Milanfar. "Nonparametric Bottom-up Saliency Detection by Self-Resemblance." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009.](https://mlanthology.org/cvprw/2009/seo2009cvprw-nonparametric/) doi:10.1109/CVPRW.2009.5204207

BibTeX

@inproceedings{seo2009cvprw-nonparametric,
  title     = {{Nonparametric Bottom-up Saliency Detection by Self-Resemblance}},
  author    = {Seo, Hae Jong and Milanfar, Peyman},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2009},
  pages     = {45-52},
  doi       = {10.1109/CVPRW.2009.5204207},
  url       = {https://mlanthology.org/cvprw/2009/seo2009cvprw-nonparametric/}
}