Learning a sequential search for landmarks

Saurabh Singh, Derek Hoiem, David Forsyth

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

Abstract

We propose a general method to find landmarks in images of objects using both appearance and spatial context. This method is applied without changes to two problems: parsing human body layouts, and finding landmarks in images of birds. Our method learns a sequential search for localizing landmarks, iteratively detecting new landmarks given the appearance and contextual information from the already detected ones. The choice of landmark to be added is opportunistic and depends on the image; for example, in one image a head-shoulder group might be expanded to a head-shoulder-hip group but in a different image to a head-shoulder-elbow group. The choice of initial landmark is similarly image dependent. Groups are scored using a learned function, which is used to expand them greedily. Our scoring function is learned from data labelled with landmarks but without any labeling of a detection order. Our method represents a novel spatial model for the kinematics of groups of landmarks, and displays strong performance on two different model problems.

Original languageEnglish (US)
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages3422-3430
Number of pages9
ISBN (Electronic)9781467369640
DOIs
StatePublished - Oct 14 2015
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: Jun 7 2015Jun 12 2015

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume07-12-June-2015
ISSN (Print)1063-6919

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period6/7/156/12/15

Fingerprint

Birds
Labeling
Kinematics

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Singh, S., Hoiem, D., & Forsyth, D. (2015). Learning a sequential search for landmarks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 3422-3430). [7298964] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298964

Learning a sequential search for landmarks. / Singh, Saurabh; Hoiem, Derek; Forsyth, David.

IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 3422-3430 7298964 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

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

Singh, S, Hoiem, D & Forsyth, D 2015, Learning a sequential search for landmarks. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298964, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 3422-3430, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 6/7/15. https://doi.org/10.1109/CVPR.2015.7298964
Singh S, Hoiem D, Forsyth D. Learning a sequential search for landmarks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society. 2015. p. 3422-3430. 7298964. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2015.7298964
Singh, Saurabh ; Hoiem, Derek ; Forsyth, David. / Learning a sequential search for landmarks. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. pp. 3422-3430 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{b35a0990ae30472e8828223f943e8fb5,
title = "Learning a sequential search for landmarks",
abstract = "We propose a general method to find landmarks in images of objects using both appearance and spatial context. This method is applied without changes to two problems: parsing human body layouts, and finding landmarks in images of birds. Our method learns a sequential search for localizing landmarks, iteratively detecting new landmarks given the appearance and contextual information from the already detected ones. The choice of landmark to be added is opportunistic and depends on the image; for example, in one image a head-shoulder group might be expanded to a head-shoulder-hip group but in a different image to a head-shoulder-elbow group. The choice of initial landmark is similarly image dependent. Groups are scored using a learned function, which is used to expand them greedily. Our scoring function is learned from data labelled with landmarks but without any labeling of a detection order. Our method represents a novel spatial model for the kinematics of groups of landmarks, and displays strong performance on two different model problems.",
author = "Saurabh Singh and Derek Hoiem and David Forsyth",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7298964",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "3422--3430",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

}

TY - GEN

T1 - Learning a sequential search for landmarks

AU - Singh, Saurabh

AU - Hoiem, Derek

AU - Forsyth, David

PY - 2015/10/14

Y1 - 2015/10/14

N2 - We propose a general method to find landmarks in images of objects using both appearance and spatial context. This method is applied without changes to two problems: parsing human body layouts, and finding landmarks in images of birds. Our method learns a sequential search for localizing landmarks, iteratively detecting new landmarks given the appearance and contextual information from the already detected ones. The choice of landmark to be added is opportunistic and depends on the image; for example, in one image a head-shoulder group might be expanded to a head-shoulder-hip group but in a different image to a head-shoulder-elbow group. The choice of initial landmark is similarly image dependent. Groups are scored using a learned function, which is used to expand them greedily. Our scoring function is learned from data labelled with landmarks but without any labeling of a detection order. Our method represents a novel spatial model for the kinematics of groups of landmarks, and displays strong performance on two different model problems.

AB - We propose a general method to find landmarks in images of objects using both appearance and spatial context. This method is applied without changes to two problems: parsing human body layouts, and finding landmarks in images of birds. Our method learns a sequential search for localizing landmarks, iteratively detecting new landmarks given the appearance and contextual information from the already detected ones. The choice of landmark to be added is opportunistic and depends on the image; for example, in one image a head-shoulder group might be expanded to a head-shoulder-hip group but in a different image to a head-shoulder-elbow group. The choice of initial landmark is similarly image dependent. Groups are scored using a learned function, which is used to expand them greedily. Our scoring function is learned from data labelled with landmarks but without any labeling of a detection order. Our method represents a novel spatial model for the kinematics of groups of landmarks, and displays strong performance on two different model problems.

UR - http://www.scopus.com/inward/record.url?scp=84959183764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959183764&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298964

DO - 10.1109/CVPR.2015.7298964

M3 - Conference contribution

AN - SCOPUS:84959183764

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3422

EP - 3430

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

ER -