Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published October 2008 | Accepted Version
Book Section - Chapter Open

Some Objects Are More Equal Than Others: Measuring and Predicting Importance

Abstract

We observe that everyday images contain dozens of objects, and that humans, in describing these images, give different priority to these objects. We argue that a goal of visual recognition is, therefore, not only to detect and classify objects but also to associate with each a level of priority which we call 'importance'. We propose a definition of importance and show how this may be estimated reliably from data harvested from human observers. We conclude by showing that a first-order estimate of importance may be computed from a number of simple image region measurements and does not require access to image meaning.

Additional Information

© Springer 2008. This material is based up on work supported under a National Science Foundation Graduate Research Fellowship, National Institute of Mental Health grant T32MH019138, Office of Naval Research grant N00014-06-1-0734, and National Institutes of Health grant R01 DA022777. We would like to thank Antonio Torralba for insightful discussions and Ryan Gomes and Kristin Branson for useful corrections.

Attached Files

Accepted Version - spainPerona08.pdf

Files

spainPerona08.pdf
Files (1.1 MB)
Name Size Download all
md5:e1acb0afc5e42b583f8f993b3aff7f5f
1.1 MB Preview Download

Additional details

Created:
August 19, 2023
Modified:
January 13, 2024