Paper doll parsing: Retrieving similar styles to parse clothing items

Kota Yamaguchi; M. Hadi Kiapour; Tamara L. Berg

doi:10.1109/ICCV.2013.437

Paper doll parsing: Retrieving similar styles to parse clothing items

Kota Yamaguchi, M. Hadi Kiapour, Tamara L. Berg

INF - System Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

212 Citations (Scopus)

Abstract

Clothing recognition is an extremely challenging problem due to wide variation in clothing item appearance, layering, and style. In this paper, we tackle the clothing parsing problem using a retrieval based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to parse the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse masks (paper doll item transfer) from retrieved examples. Experimental evaluation shows that our approach significantly outperforms state of the art in parsing accuracy.

Original language	English
Title of host publication	Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3519-3526
Number of pages	8
ISBN (Print)	9781479928392
DOIs	https://doi.org/10.1109/ICCV.2013.437
Publication status	Published - 2013 Jan 1
Event	2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia Duration: 2013 Dec 1 → 2013 Dec 8

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision

Other

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

Keywords

clothing parsing
clothing recognition
segmentation

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2013.437

Cite this

Yamaguchi, K., Kiapour, M. H., & Berg, T. L. (2013). Paper doll parsing: Retrieving similar styles to parse clothing items. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 3519-3526). [6751549] (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.437

Paper doll parsing : Retrieving similar styles to parse clothing items. / Yamaguchi, Kota; Kiapour, M. Hadi; Berg, Tamara L.

Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 3519-3526 6751549 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yamaguchi, K, Kiapour, MH & Berg, TL 2013, Paper doll parsing: Retrieving similar styles to parse clothing items. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751549, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 3519-3526, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 13/12/1. https://doi.org/10.1109/ICCV.2013.437

Yamaguchi K, Kiapour MH, Berg TL. Paper doll parsing: Retrieving similar styles to parse clothing items. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc. 2013. p. 3519-3526. 6751549. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.437

@inproceedings{4602cb780a5e4b649abec5967241906e,

title = "Paper doll parsing: Retrieving similar styles to parse clothing items",

abstract = "Clothing recognition is an extremely challenging problem due to wide variation in clothing item appearance, layering, and style. In this paper, we tackle the clothing parsing problem using a retrieval based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to parse the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse masks (paper doll item transfer) from retrieved examples. Experimental evaluation shows that our approach significantly outperforms state of the art in parsing accuracy.",

keywords = "clothing parsing, clothing recognition, segmentation",

author = "Kota Yamaguchi and Kiapour, {M. Hadi} and Berg, {Tamara L.}",

year = "2013",

month = jan,

day = "1",

doi = "10.1109/ICCV.2013.437",

language = "English",

isbn = "9781479928392",

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

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

pages = "3519--3526",

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

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

}

TY - GEN

T1 - Paper doll parsing

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

AU - Yamaguchi, Kota

AU - Kiapour, M. Hadi

AU - Berg, Tamara L.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Clothing recognition is an extremely challenging problem due to wide variation in clothing item appearance, layering, and style. In this paper, we tackle the clothing parsing problem using a retrieval based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to parse the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse masks (paper doll item transfer) from retrieved examples. Experimental evaluation shows that our approach significantly outperforms state of the art in parsing accuracy.

AB - Clothing recognition is an extremely challenging problem due to wide variation in clothing item appearance, layering, and style. In this paper, we tackle the clothing parsing problem using a retrieval based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to parse the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse masks (paper doll item transfer) from retrieved examples. Experimental evaluation shows that our approach significantly outperforms state of the art in parsing accuracy.

KW - clothing parsing

KW - clothing recognition

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=84898779488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898779488&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.437

DO - 10.1109/ICCV.2013.437

M3 - Conference contribution

AN - SCOPUS:84898779488

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 3519

EP - 3526

BT - Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 1 December 2013 through 8 December 2013

ER -

Paper doll parsing: Retrieving similar styles to parse clothing items

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this