Object recognition by scene alignment

Bryan C. Russell, Antonio Torralba, Ce Liu, Robert Fergus, William T. Freeman

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

Abstract

Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input image, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a probabilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
StatePublished - 2009
Event21st Annual Conference on Neural Information Processing Systems, NIPS 2007 - Vancouver, BC, Canada
Duration: Dec 3 2007Dec 6 2007

Other

Other21st Annual Conference on Neural Information Processing Systems, NIPS 2007
CountryCanada
CityVancouver, BC
Period12/3/0712/6/07

Fingerprint

Object recognition
Labels
Statistical Models

ASJC Scopus subject areas

  • Information Systems

Cite this

Russell, B. C., Torralba, A., Liu, C., Fergus, R., & Freeman, W. T. (2009). Object recognition by scene alignment. In Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

Object recognition by scene alignment. / Russell, Bryan C.; Torralba, Antonio; Liu, Ce; Fergus, Robert; Freeman, William T.

Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 2009.

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

Russell, BC, Torralba, A, Liu, C, Fergus, R & Freeman, WT 2009, Object recognition by scene alignment. in Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 21st Annual Conference on Neural Information Processing Systems, NIPS 2007, Vancouver, BC, Canada, 12/3/07.
Russell BC, Torralba A, Liu C, Fergus R, Freeman WT. Object recognition by scene alignment. In Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 2009
Russell, Bryan C. ; Torralba, Antonio ; Liu, Ce ; Fergus, Robert ; Freeman, William T. / Object recognition by scene alignment. Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 2009.
@inproceedings{9e6342c3717741b183e0e55891cb311a,
title = "Object recognition by scene alignment",
abstract = "Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input image, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a probabilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.",
author = "Russell, {Bryan C.} and Antonio Torralba and Ce Liu and Robert Fergus and Freeman, {William T.}",
year = "2009",
language = "English (US)",
isbn = "160560352X",
booktitle = "Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference",

}

TY - GEN

T1 - Object recognition by scene alignment

AU - Russell, Bryan C.

AU - Torralba, Antonio

AU - Liu, Ce

AU - Fergus, Robert

AU - Freeman, William T.

PY - 2009

Y1 - 2009

N2 - Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input image, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a probabilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.

AB - Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input image, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a probabilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.

UR - http://www.scopus.com/inward/record.url?scp=84863353693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863353693&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84863353693

SN - 160560352X

SN - 9781605603520

BT - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

ER -