A Caltech Library Service

Learning object categories from Google's image search

Fergus, R. and Fei-Fei, L and Perona, P. and Zisserman, A. (2005) Learning object categories from Google's image search. In: Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005. Vol.2. IEEE , Piscataway, NJ, pp. 1816-1823. ISBN 0-7695-2334-X.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate the models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasets.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, P.0000-0002-7583-5809
Additional Information:© 2005 IEEE. Financial support was provided by: EC Project CogViSys; UK EPSRC; Caltech CNSE and the NSF. This work was supported in part by the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002-506778. This publication only reflects the au thors’ views. Thanks to Rebecca Hoath and Veronica Robles for image labelling. We are indebted to Josef Sivic for his considerable help with many aspects of the paper.
Funding AgencyGrant Number
Engineering and Physical Sciences Research Council (EPSRC)UNSPECIFIED
PASCAL Network of ExcellenceIST-2002-506778
Record Number:CaltechAUTHORS:20150904-125520711
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:60079
Deposited By: Caroline Murphy
Deposited On:15 Sep 2015 00:03
Last Modified:10 Nov 2021 22:29

Repository Staff Only: item control page