MDL Patch Correspondences on Unlabeled Images with Occlusions
Författare
Summary, in English
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.
Avdelning/ar
Publiceringsår
2008
Språk
Engelska
Sidor
999-1006
Publikation/Tidskrift/Serie
2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops)
Dokumenttyp
Konferensbidrag
Ämne
- Mathematics
Nyckelord
- computational geometry
- image processing
- MDL patch correspondence
- unlabeled images
- occlusions
- automatic construction
- shape model
- appearance model
- training set
- minimum description length
- automatic model building
Conference name
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2008
Conference date
2008-06-23 - 2008-06-28
Conference place
Anchorage, Alaska, United States
Status
Published
ISBN/ISSN/Övrigt
- ISBN: 978-1-4244-2339-2