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

@inproceedings{Murphy2003UsingTF,
  title={Using the Forest to See the Trees : A Graphical Model Relating Features , Objects , and Scenes},
  author={Kevin Murphy and Antonio Torralba and William T. Freeman},
  year={2003}
}
Standard approaches to object detection focus on local patc hes of the image, and try to classify them as background or not. We propo se t use thescene 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 detectio n and scene classification. 
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 512 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 296 extracted citations

Pruning training sets for learning of object categories

2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) • 2005
View 4 Excerpts
Highly Influenced

Geospatial object recognition from high resolution satellite imagery

2013 21st Signal Processing and Communications Applications Conference (SIU) • 2013
View 4 Excerpts
Highly Influenced

Learning Behavioural Context

International Journal of Computer Vision • 2011
View 4 Excerpts
Highly Influenced

512 Citations

0204060'06'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 512 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…