ML Anthology

Object Categorization Using Co-Occurrence, Location and Appearance

Carolina Galleguillos, Andrew Rabinovich, Serge J. Belongie
CVPR 2008
doi:10.1109/CVPR.2008.4587799 /cvpr/2008/galleguillos2008cvpr-object/

Abstract

In this work we introduce a novel approach to object categorization that incorporates two types of context-co-occurrence and relative location - with local appearance-based features. Our approach, named CoLA (for co-occurrence, location and appearance), uses a conditional random field (CRF) to maximize object label agreement according to both semantic and spatial relevance. We model relative location between objects using simple pairwise features. By vector quantizing this feature space, we learn a small set of prototypical spatial relationships directly from the data. We evaluate our results on two challenging datasets: PASCAL 2007 and MSRC. The results show that combining co-occurrence and spatial context improves accuracy in as many as half of the categories compared to using co-occurrence alone.

PDF CVPR Semantic Scholar

Cite

Text

Galleguillos et al. "Object Categorization Using Co-Occurrence, Location and Appearance." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587799

Markdown

[Galleguillos et al. "Object Categorization Using Co-Occurrence, Location and Appearance." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/galleguillos2008cvpr-object/) doi:10.1109/CVPR.2008.4587799

BibTeX

@inproceedings{galleguillos2008cvpr-object,
  title     = {{Object Categorization Using Co-Occurrence, Location and Appearance}},
  author    = {Galleguillos, Carolina and Rabinovich, Andrew and Belongie, Serge J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587799},
  url       = {https://mlanthology.org/cvpr/2008/galleguillos2008cvpr-object/}
}