Andreetto, Marco and Zelnik-Manor, Lihi and Perona, Pietro (2008) Unsupervised learning of categorical segments in image collections. In: Computer Vision and Pattern Recognition Workshops, 2008. Proceedings – IEEE Computer Society Conference on Computer Vision and Pattern Recognition . IEEE , pp. 158-165. ISBN 978-1-4244-2339-2 http://resolver.caltech.edu/CaltechAUTHORS:20100622-150143532
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20100622-150143532
Which one comes first: segmentation or recognition? We propose a probabilistic framework for carrying out the two simultaneously. The framework combines an LDA ‘bag of visual words’ model for recognition, and a hybrid parametric-nonparametric model for segmentation. If applied to a collection of images, our framework can simultaneously discover the segments of each image, and the correspondence between such segments. Such segments may be thought of as the ‘parts’ of corresponding objects that appear in the image collection. Thus, the model may be used for learning new categories, detecting/classifying objects, and segmenting images.
|Item Type:||Book Section|
|Additional Information:||© 2008 IEEE. Funding for this research was provided by ONR-MURI Grant N00014-06-1-0734. Lihi Zelnik-Manor is supported by FP7-IRG grant 2009783.|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||09 Jul 2010 16:51|
|Last Modified:||26 Dec 2012 12:09|
Repository Staff Only: item control page