ML Anthology

Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes

Kevin P. Murphy, Antonio Torralba, William T. Freeman
NeurIPS 2003 pp. 1499-1506
/neurips/2003/murphy2003neurips-using/

Abstract

Standard approaches to object detection focus on local patches of the image, and try to classify them as background or not. We propose to use the scene context (image as a whole) as an extra source of (global) information, to help resolve local ambiguities. We present a conditional random field for jointly solving the tasks of object detection and scene classification.

PDF NeurIPS Semantic Scholar

Cite

Text

Murphy et al. "Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes." Neural Information Processing Systems, 2003.

Markdown

[Murphy et al. "Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/murphy2003neurips-using/)

BibTeX

@inproceedings{murphy2003neurips-using,
  title     = {{Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes}},
  author    = {Murphy, Kevin P. and Torralba, Antonio and Freeman, William T.},
  booktitle = {Neural Information Processing Systems},
  year      = {2003},
  pages     = {1499-1506},
  url       = {https://mlanthology.org/neurips/2003/murphy2003neurips-using/}
}