Formulating semantic image annotation as a supervised learning problem

  title={Formulating semantic image annotation as a supervised learning problem},
  author={Gustavo Carneiro and Nuno Vasconcelos},
  journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  pages={163-168 vol. 2}
We introduce a new method to automatically annotate and retrieve images using a vocabulary of image semantics. The novel contributions include a discriminant formulation of the problem, a multiple instance learning solution that enables the estimation of concept probability distributions without prior image segmentation, and a hierarchical description of the density of each image class that enables very efficient training. Compared to current methods of image annotation and retrieval, the one… CONTINUE READING
Highly Influential
This paper has highly influenced 23 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 231 citations. REVIEW CITATIONS


Publications citing this paper.

231 Citations

Citations per Year
Semantic Scholar estimates that this publication has 231 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…