Shape discovery from unlabeled image collections

  title={Shape discovery from unlabeled image collections},
  author={Yong Jae Lee and Kristen Grauman},
  journal={2009 IEEE Conference on Computer Vision and Pattern Recognition},
Can we discover common object shapes within unlabeled multi-category collections of images? While often a critical cue at the category-level, contour matches can be difficult to isolate reliably from edge clutter-even within labeled images from a known class, let alone unlabeled examples. We propose a shape discovery method in which local appearance (patch) matches serve to anchor the surrounding edge fragments, yielding a more reliable affinity function for images that accounts for both shape… CONTINUE READING
Highly Cited
This paper has 76 citations. REVIEW CITATIONS
52 Citations
27 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 52 extracted citations

76 Citations

Citations per Year
Semantic Scholar estimates that this publication has 76 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 27 references

Similar Papers

Loading similar papers…