Object / Background Scene Joint Classification in Photographs Using Linguistic Statistics from the Web

@inproceedings{Greffenstette2008ObjectB,
  title={Object / Background Scene Joint Classification in Photographs Using Linguistic Statistics from the Web},
  author={Gregory Greffenstette and Pierre-Alain Mo{\"e}llic and Christophe Millet},
  year={2008}
}
Object and scene recognition is widely recognized as a diffic ult problem in computer vision. We present here an approach t o t is problem that merges recognition of an object and its backgro und. Relying on the assumption that given objects are strong ly linked to given background scenes (a deer is more likely to appear in a f orest than on an iceberg), we learn object classifiers using j o t estimations of object and scene. Such an approach would normally require a large quantity of training… CONTINUE READING
3 Citations
21 References
Similar Papers

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…