Discovering States and Transformations in Image Collections.

Isola, P., Lim, J. J., Adelson, E. H.


Abstract

Objects in visual scenes come in a rich variety of transformed states. A few classes of transformation have been heavily studied in computer vision: mostly simple, parametric changes in color and geometry. However, transformations in the physical world occur in many more flavors, and they come with semantic meaning: e.g., bending, folding, aging, etc. The transformations an object can undergo tell us about its physical and functional properties. In this paper, we introduce a dataset of objects, scenes, and materials, each of which is found in a variety of transformed states. Given a novel collection of images, we show how to explain the collection in terms of the states and transformations it depicts. Our system works by generalizing across object classes: states and transformations learned on one set of objects are used to interpret the image collection for an entirely new object class.

Information

title:
Discovering States and Transformations in Image Collections.
author:
Isola,
P.,
Lim,
J. J.,
Adelson,
E. H.
citation:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
shortcite:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
year:
2015
created:
2015-01-01
keyword:
adelson
www:
http://persci.mit.edu/pub_abstracts/discovering-states-transformations.html
pdf:
http://persci.mit.edu/pub_pdfs/discovering-states-transformations.pdf
pageid:
discovering-states-transformations
type:
publication