loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 2
Names and Faces in the News
Washington, D.C., USA
June 27-July 02
ISBN: 0-7695-2158-4
ASCII Text
x 
 
Tamara L. Berg, Alexander C. Berg, Jaety Edwards, Michael Maire, Ryan White, Yee-Whye Teh, Erik Learned-Miller, D. A. Forsyth, "Names and Faces in the News," Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, vol. 2, pp. 848-854, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 2, 2004.
 
 
BibTex
x
 
@article{ 10.1109/CVPR.2004.175,
author = {Tamara L. Berg and Alexander C. Berg and Jaety Edwards and Michael Maire and Ryan White and Yee-Whye Teh and Erik Learned-Miller and D. A. Forsyth},
title = {Names and Faces in the News},
journal ={Computer Vision and Pattern Recognition, IEEE Computer Society Conference on},
volume = {2},
year = {2004},
issn = {1063-6919},
pages = {848-854},
doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2004.175},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
TI - Names and Faces in the News
SN - 1063-6919
SP848
EP854
A1 - Tamara L. Berg,
A1 - Alexander C. Berg,
A1 - Jaety Edwards,
A1 - Michael Maire,
A1 - Ryan White,
A1 - Yee-Whye Teh,
A1 - Erik Learned-Miller,
A1 - D. A. Forsyth,
PY - 2004
KW - null
VL - 2
JA - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
ER -
 
Tamara L. Berg, University of California at Berkeley
Alexander C. Berg, University of California at Berkeley
Jaety Edwards, University of California at Berkeley
Michael Maire, University of California at Berkeley
Ryan White, University of California at Berkeley
Yee-Whye Teh, University of California at Berkeley
Erik Learned-Miller, University of California at Berkeley
D. A. Forsyth, University of California at Berkeley

We show quite good face clustering is possible for a dataset of inaccurately and ambiguously labelled face images. Our dataset is 44,773 face images, obtained by applying a face finder to approximately half a million captioned news images. This dataset is more realistic than usual face recognition datasets, because it contains faces captured "in the wild" in a variety of configurations with respect to the camera, taking a variety of expressions, and under illumination of widely varying color. Each face image is associated with a set of names, automatically extracted from the associated caption. Many, but not all such sets contain the correct name.

We cluster face images in appropriate discriminant coordinates. We use a clustering procedure to break ambiguities in labelling and identify incorrectly labelled faces. A merging procedure then identifies variants of names that refer to the same individual. The resulting representation can be used to label faces in news images or to organize news pictures by individuals present.

An alternative view of our procedure is as a process that cleans up noisy supervised data. We demonstrate how to use entropy measures to evaluate such procedures.

Citation:
Tamara L. Berg, Alexander C. Berg, Jaety Edwards, Michael Maire, Ryan White, Yee-Whye Teh, Erik Learned-Miller, D. A. Forsyth, "Names and Faces in the News," cvpr, vol. 2, pp.848-854, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 2, 2004
Usage of this product signifies your acceptance of the Terms of Use.