Learning object categories from Google's image search

R. Fergus, L. Fei-Fei, P. Perona, A. Zisserman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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 infra-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.

Original languageEnglish (US)
Title of host publicationProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages1816-1823
Number of pages8
VolumeII
DOIs
StatePublished - 2005
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: Oct 17 2005Oct 20 2005

Other

OtherProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
CountryChina
CityBeijing
Period10/17/0510/20/05

Fingerprint

Search engines
Object recognition
Internet

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Fergus, R., Fei-Fei, L., Perona, P., & Zisserman, A. (2005). Learning object categories from Google's image search. In Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 (Vol. II, pp. 1816-1823). [1544937] https://doi.org/10.1109/ICCV.2005.142

Learning object categories from Google's image search. / Fergus, R.; Fei-Fei, L.; Perona, P.; Zisserman, A.

Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. Vol. II 2005. p. 1816-1823 1544937.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fergus, R, Fei-Fei, L, Perona, P & Zisserman, A 2005, Learning object categories from Google's image search. in Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. vol. II, 1544937, pp. 1816-1823, Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, 10/17/05. https://doi.org/10.1109/ICCV.2005.142
Fergus R, Fei-Fei L, Perona P, Zisserman A. Learning object categories from Google's image search. In Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. Vol. II. 2005. p. 1816-1823. 1544937 https://doi.org/10.1109/ICCV.2005.142
Fergus, R. ; Fei-Fei, L. ; Perona, P. ; Zisserman, A. / Learning object categories from Google's image search. Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. Vol. II 2005. pp. 1816-1823
@inproceedings{290672763efe4851b397583b1a991f2d,
title = "Learning object categories from Google's image search",
abstract = "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 infra-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.",
author = "R. Fergus and L. Fei-Fei and P. Perona and A. Zisserman",
year = "2005",
doi = "10.1109/ICCV.2005.142",
language = "English (US)",
isbn = "076952334X",
volume = "II",
pages = "1816--1823",
booktitle = "Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005",

}

TY - GEN

T1 - Learning object categories from Google's image search

AU - Fergus, R.

AU - Fei-Fei, L.

AU - Perona, P.

AU - Zisserman, A.

PY - 2005

Y1 - 2005

N2 - 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 infra-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.

AB - 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 infra-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.

UR - http://www.scopus.com/inward/record.url?scp=33745839880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745839880&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2005.142

DO - 10.1109/ICCV.2005.142

M3 - Conference contribution

SN - 076952334X

SN - 9780769523347

VL - II

SP - 1816

EP - 1823

BT - Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

ER -