A sparse object category model for efficient learning and exhaustive recognition

R. Fergus, P. Perona, A. Zisserman

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

Abstract

We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semisupervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in an exhaustive manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.

Original languageEnglish (US)
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
EditorsC. Schmid, S. Soatto, C. Tomasi
Pages380-387
Number of pages8
Volume1
DOIs
StatePublished - 2005
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: Jun 20 2005Jun 25 2005

Other

Other2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
CountryUnited States
CitySan Diego, CA
Period6/20/056/25/05

Fingerprint

Detectors
Object recognition
Model structures
Stars
Topology

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering
  • Engineering(all)

Cite this

Fergus, R., Perona, P., & Zisserman, A. (2005). A sparse object category model for efficient learning and exhaustive recognition. In C. Schmid, S. Soatto, & C. Tomasi (Eds.), Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 (Vol. 1, pp. 380-387) https://doi.org/10.1109/CVPR.2005.47

A sparse object category model for efficient learning and exhaustive recognition. / Fergus, R.; Perona, P.; Zisserman, A.

Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. ed. / C. Schmid; S. Soatto; C. Tomasi. Vol. 1 2005. p. 380-387.

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

Fergus, R, Perona, P & Zisserman, A 2005, A sparse object category model for efficient learning and exhaustive recognition. in C Schmid, S Soatto & C Tomasi (eds), Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. vol. 1, pp. 380-387, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, United States, 6/20/05. https://doi.org/10.1109/CVPR.2005.47
Fergus R, Perona P, Zisserman A. A sparse object category model for efficient learning and exhaustive recognition. In Schmid C, Soatto S, Tomasi C, editors, Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. Vol. 1. 2005. p. 380-387 https://doi.org/10.1109/CVPR.2005.47
Fergus, R. ; Perona, P. ; Zisserman, A. / A sparse object category model for efficient learning and exhaustive recognition. Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. editor / C. Schmid ; S. Soatto ; C. Tomasi. Vol. 1 2005. pp. 380-387
@inproceedings{e45f990bb3134249a18c3fbe1cd7bda4,
title = "A sparse object category model for efficient learning and exhaustive recognition",
abstract = "We present a {"}parts and structure{"} model for object category recognition that can be learnt efficiently and in a semisupervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in an exhaustive manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.",
author = "R. Fergus and P. Perona and A. Zisserman",
year = "2005",
doi = "10.1109/CVPR.2005.47",
language = "English (US)",
isbn = "0769523722",
volume = "1",
pages = "380--387",
editor = "C. Schmid and S. Soatto and C. Tomasi",
booktitle = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",

}

TY - GEN

T1 - A sparse object category model for efficient learning and exhaustive recognition

AU - Fergus, R.

AU - Perona, P.

AU - Zisserman, A.

PY - 2005

Y1 - 2005

N2 - We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semisupervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in an exhaustive manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.

AB - We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semisupervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in an exhaustive manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.

UR - http://www.scopus.com/inward/record.url?scp=24644483228&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24644483228&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2005.47

DO - 10.1109/CVPR.2005.47

M3 - Conference contribution

SN - 0769523722

VL - 1

SP - 380

EP - 387

BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

A2 - Schmid, C.

A2 - Soatto, S.

A2 - Tomasi, C.

ER -