The Joint Manifold Model for Semi-supervised Multi-valued Regression

@article{Navaratnam2007TheJM,
  title={The Joint Manifold Model for Semi-supervised Multi-valued Regression},
  author={Ramanan Navaratnam and Andrew W. Fitzgibbon and Roberto Cipolla},
  journal={2007 IEEE 11th International Conference on Computer Vision},
  year={2007},
  pages={1-8}
}
Many computer vision tasks may be expressed as the problem of learning a mapping between image space and a parameter space. For example, in human body pose estimation, recent research has directly modelled the mapping from image features (z) to joint angles (thetas). Fitting such models requires training data in the form of labelled (z, thetas) pairs, from which are learned the conditional densities p(thetas\z). Inference is then simple: given test image features z, the conditional p(thetas\z… CONTINUE READING
Highly Cited
This paper has 134 citations. REVIEW CITATIONS
77 Citations
22 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 77 extracted citations

134 Citations

0102030'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 134 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 22 references

Website and technical report, http://www.research.microsoft.com/∼awf/jmm

  • R. Navaratnam, A. W. Fitzgibbon, R. Cipolla
  • The Joint Manifold Model,
  • 2007
2 Excerpts

Similar Papers

Loading similar papers…