Learning to Traverse Image Manifolds

@inproceedings{Dollr2006LearningTT,
  title={Learning to Traverse Image Manifolds},
  author={Piotr Doll{\'a}r and Serge J. Belongie and Vincent Rabaud},
  booktitle={NIPS},
  year={2006}
}
Original image convolved (F i = X ) Piotr Dollár Computer Science and Engineering University of California, San Diego pdollar@cs.ucsd.edu We present a new algorithm, Locally Smooth Manifold Learning ( ), that learns a warping function from a point on an image manifold to its neighbors. Important characteristics of include the ability to recover the structure of the manifold in sparsely populated regions and beyond the support of the provided data. Applications of our proposed technique include… CONTINUE READING
Highly Cited
This paper has 63 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
39 Citations
24 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 39 extracted citations

63 Citations

01020'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 63 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 24 references

Learning to traverse image manifolds

  • P. Dollár, V. Rabaud, S. Belongie
  • Technical Report
  • 2007
Highly Influential
3 Excerpts

L

  • E. Di Bernardo
  • Goncalves and P. Perona.US Patent 6,552,729…
  • 2003

Think globally

  • L. K. Saul, S. T. Roweis
  • fit locally: unsupervised learning of low…
  • 2003
1 Excerpt

Similar Papers

Loading similar papers…