Estimating scene typicality from human ratings and image features
Name
Oliva-2011-Estimating scene typicality.pdf
Size
969.32 KB
Format
Adobe PDF
Checksum (MD5)
4076dc430827a6afc72411d51aa9a3eb
Author(s)
Ehinger, Krista A.
Xiao, Jianxiong
Torralba, Antonio
Oliva, Aude
Date Issued
July 2011
Journal
Proceedings of the 33rd Annual Cognitive Science Conference, COGSCI 2011, Boston, Massachusetts, Wednesday, July 20 - Saturday July 23, 2011
Publisher
Cognitive Science Society, Inc.
Citation
Ehinger, Krista A. et al. "Estimating scene typicality from human ratings and image features." in Proceedings of the 33rd Annual Cognitive Science Conference, COGSCI 2011.
Version
Author's final manuscript
Abstract
Scenes, like objects, are visual entities that can be categorized into functional and semantic groups. One of the core concepts of human categorization is the idea that category membership is graded: some exemplars are more typical than others. Here, we obtain human typicality rankings for more than 120,000 images from 706 scene categories through an online rating task on Amazon Mechanical Turk. We use these rankings to identify the most typical examples of each scene category. Using computational models of scene classification based on global image features, we find that images which are rated as more typical examples of their category are more likely to be classified correctly. This indicates that the most typical scene examples contain the diagnostic visual features that are relevant for their categorization. Objectless, holistic representations of scenes might serve as a good basis for understanding how semantic categories are defined in term of perceptual representations.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
http://palm.mindmodeling.org/cogsci2011/papers/0600/paper0600.pdf
