A Compositional Model for Low-Dimensional Image Set Representation

Author(s)
Mobahi, Hossein; Liu, Ce; Freeman, William T.
Thumbnail
DownloadFreeman_A compositional.pdf (5.364Mb)
OPEN_ACCESS_POLICY
Terms of use
Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/
Metadata
Show full item record
Abstract
Learning a low-dimensional representation of images is useful for various applications in graphics and computer vision. Existing solutions either require manually specified landmarks for corresponding points in the images, or are restricted to specific objects or shape deformations. This paper alleviates these limitations by imposing a specific model for generating images, the nested composition of color, shape, and appearance. We show that each component can be approximated by a low-dimensional subspace when the others are factored out. Our formulation allows for efficient learning and experiments show encouraging results.
Date issued
2014-06
URI
http://hdl.handle.net/1721.1/100401
Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Journal
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Mobahi, Hossein, Ce Liu, and William T. Freeman. “A Compositional Model for Low-Dimensional Image Set Representation.” 2014 IEEE Conference on Computer Vision and Pattern Recognition (June 2014).
Version: Author's final manuscript
ISBN
978-1-4799-5118-5
Collections