ML Anthology

Statistical Context Priming for Object Detection

Antonio Torralba, Pawan Sinha
ICCV 2001 pp. 763-770
doi:10.1109/ICCV.2001.10051 /iccv/2001/torralba2001iccv-statistical/

Abstract

There is general consensus that context can be a rich source of information about an object's identity, location and scale. However the issue of how to formalize centextual influences is still largely open. Here we introduce a simple probabilistic framework for modeling the relationship between context and object properties. We represent global context information in terms of the spatial layout of spectral components. The resulting scheme serves as an effective procedure for context driven focus of attention and scale-selection on real-world scenes. Based on a simple holistic analysis of an image, the scheme is able to accurately predict object locations and sizes.

ICCV Semantic Scholar

Cite

Text

Torralba and Sinha. "Statistical Context Priming for Object Detection." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.10051

Markdown

[Torralba and Sinha. "Statistical Context Priming for Object Detection." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/torralba2001iccv-statistical/) doi:10.1109/ICCV.2001.10051

BibTeX

@inproceedings{torralba2001iccv-statistical,
  title     = {{Statistical Context Priming for Object Detection}},
  author    = {Torralba, Antonio and Sinha, Pawan},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {763-770},
  doi       = {10.1109/ICCV.2001.10051},
  url       = {https://mlanthology.org/iccv/2001/torralba2001iccv-statistical/}
}