A Caltech Library Service

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

Spain, Merrielle and Perona, Pietro (2008) Some Objects Are More Equal Than Others: Measuring and Predicting Importance. In: Computer Vision – ECCV 2008. Lecture Notes in Comptuer Science. Vol.1. No.5302. Springer , Berlin, pp. 523-536. ISBN 978-3-540-88681-5.

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
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.
Funding AgencyGrant Number
NSF Graduate Research FellowshipUNSPECIFIED
NIH Predoctoral FellowshipT32MH019138
Office of Naval Research (ONR)N00014-06-1-0734
NIHR01 DA022777
Subject Keywords:Image Processing and Computer Vision Computer Imaging, Vision, Pattern Recognition and Graphics Computer Graphics Pattern Recognition Data Mining and Knowledge Discovery Computer Appl. in Arts and Humanities
Series Name:Lecture Notes in Comptuer Science
Issue or Number:5302
Record Number:CaltechAUTHORS:20140730-101716572
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47593
Deposited By: Caroline Murphy
Deposited On:25 Aug 2014 21:41
Last Modified:03 Oct 2019 06:55

Repository Staff Only: item control page