ML Anthology

MDL Patch Correspondences on Unlabeled Images with Occlusions

Johan Karlsson, Kalle Åström
CVPRW 2008 pp. 1-8
doi:10.1109/CVPRW.2008.4563085 /cvprw/2008/karlsson2008cvprw-mdl/

Abstract

Automatic construction of Shape and Appearance Models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing correspondences of high quality is minimum description length (MDL). In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts have been successful for automatic model building. In this paper it is shown how to fuse the above approaches and use MDL to fully automatically build optimal parts+geometry models from unlabeled images.

PDF CVPRW Semantic Scholar

Cite

Text

Karlsson and Åström. "MDL Patch Correspondences on Unlabeled Images with Occlusions." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008. doi:10.1109/CVPRW.2008.4563085

Markdown

[Karlsson and Åström. "MDL Patch Correspondences on Unlabeled Images with Occlusions." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008.](https://mlanthology.org/cvprw/2008/karlsson2008cvprw-mdl/) doi:10.1109/CVPRW.2008.4563085

BibTeX

@inproceedings{karlsson2008cvprw-mdl,
  title     = {{MDL Patch Correspondences on Unlabeled Images with Occlusions}},
  author    = {Karlsson, Johan and Åström, Kalle},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2008},
  pages     = {1-8},
  doi       = {10.1109/CVPRW.2008.4563085},
  url       = {https://mlanthology.org/cvprw/2008/karlsson2008cvprw-mdl/}
}