A bootstrapping algorithm for learning linear models of object classes

  title={A bootstrapping algorithm for learning linear models of object classes},
  author={Thomas Vetter and Michael J. Jones and Tomaso A. Poggio},
Flexible models of object classes, based on linear combinations of prototypical images, are capable of matching novel images of the same class and have been shown to be a powerful tool to solve several fundamental vision tasks such as recognition, synthesis and correspondence. The key problem in creating a speci c exible model is the computation of pixelwise correspondence between the prototypes, a task done until now in a semiautomatic way. In this paper we describe an algorithm that… CONTINUE READING
Highly Cited
This paper has 155 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
97 Citations
25 References
Similar Papers


Publications citing this paper.

156 Citations

Citations per Year
Semantic Scholar estimates that this publication has 156 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…