ML Anthology

Top-Down Color Attention for Object Recognition

Fahad Shahbaz Khan, Joost van de Weijer, María Vanrell
ICCV 2009 pp. 979-986
doi:10.1109/ICCV.2009.5459362 /iccv/2009/khan2009iccv-top/

Abstract

Generally the bag-of-words based image representation follows a bottom-up paradigm. The subsequent stages of the process: feature detection, feature description, vocabulary construction and image representation are performed independent of the intentioned object classes to be detected. In such a framework, combining multiple cues such as shape and color often provides below-expected results.

ICCV Semantic Scholar

Cite

Text

Khan et al. "Top-Down Color Attention for Object Recognition." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459362

Markdown

[Khan et al. "Top-Down Color Attention for Object Recognition." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/khan2009iccv-top/) doi:10.1109/ICCV.2009.5459362

BibTeX

@inproceedings{khan2009iccv-top,
  title     = {{Top-Down Color Attention for Object Recognition}},
  author    = {Khan, Fahad Shahbaz and van de Weijer, Joost and Vanrell, María},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2009},
  pages     = {979-986},
  doi       = {10.1109/ICCV.2009.5459362},
  url       = {https://mlanthology.org/iccv/2009/khan2009iccv-top/}
}