Multi-instance object segmentation with exemplars

Xuming He; Stephen Gould

doi:10.1109/ICCVW.2013.9

Multi-instance object segmentation with exemplars

Xuming He, Stephen Gould

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

1 Citation (Scopus)

Abstract

We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of multi-instance segmentation using a small set of annotated reference images. We design a novel CRF model that jointly models object appearance, shape deformation, and object occlusion at the super pixel level. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and layout adaptation.

Original language	English
Title of host publication	Proceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Print)	9781479930227
DOIs	https://doi.org/10.1109/ICCVW.2013.9
Publication status	Published - 2013
Event	2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013 - Sydney, NSW, Australia Duration: 1 Dec 2013 → 8 Dec 2013

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision

Conference

Conference	2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013
Country/Territory	Australia
City	Sydney, NSW
Period	1/12/13 → 8/12/13

Access to Document

10.1109/ICCVW.2013.9

Cite this

@inproceedings{0c4d5a4688044a5fb2d5e0cb2c1e0c77,

title = "Multi-instance object segmentation with exemplars",

abstract = "We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of multi-instance segmentation using a small set of annotated reference images. We design a novel CRF model that jointly models object appearance, shape deformation, and object occlusion at the super pixel level. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and layout adaptation.",

author = "Xuming He and Stephen Gould",

year = "2013",

doi = "10.1109/ICCVW.2013.9",

language = "English",

isbn = "9781479930227",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--4",

booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013",

address = "United States",

note = "2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013 ; Conference date: 01-12-2013 Through 08-12-2013",

}

He, X & Gould, S 2013, Multi-instance object segmentation with exemplars. in Proceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013., 6755871, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013, Sydney, NSW, Australia, 1/12/13. https://doi.org/10.1109/ICCVW.2013.9

Multi-instance object segmentation with exemplars. / He, Xuming; Gould, Stephen.
Proceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 1-4 6755871 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

TY - GEN

T1 - Multi-instance object segmentation with exemplars

AU - He, Xuming

AU - Gould, Stephen

PY - 2013

Y1 - 2013

N2 - We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of multi-instance segmentation using a small set of annotated reference images. We design a novel CRF model that jointly models object appearance, shape deformation, and object occlusion at the super pixel level. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and layout adaptation.

AB - We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of multi-instance segmentation using a small set of annotated reference images. We design a novel CRF model that jointly models object appearance, shape deformation, and object occlusion at the super pixel level. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and layout adaptation.

UR - http://www.scopus.com/inward/record.url?scp=84897492442&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2013.9

DO - 10.1109/ICCVW.2013.9

M3 - Conference Paper

SN - 9781479930227

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1

EP - 4

BT - Proceedings - 2013 IEEE International Conference on Computer Vision Workshops, ICCVW 2013

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013

Y2 - 1 December 2013 through 8 December 2013

ER -

Multi-instance object segmentation with exemplars

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this