Kin-verification model on FIW dataset using multi-set Learning and local features

Eran Dahan; Yosi Keller; Shahar Mahpod

doi:10.1145/3134421.3134423

Kin-verification model on FIW dataset using multi-set Learning and local features

Eran Dahan, Yosi Keller, Shahar Mahpod

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

14 Scopus citations

Abstract

Kinship Verification of two or more people has shown to be a complicated problem, though it is widely used in various practical tasks and applications. The areas of the use-cases vary. Among themare applications for homeland security, automatic family recognition, youth and elder matching or predicting and more. We propose using Deep Learning approach to deal with the problem of Kin Verification, such to provide a logical explanation for solving the problem with a novel mechanism for training on the FIW data-set. Our method obtains state-of-the-art for the FIW challenge for the restricted-image setting.¹

Original language	English
Title of host publication	RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017
Publisher	Association for Computing Machinery, Inc
Pages	31-35
Number of pages	5
ISBN (Electronic)	9781450355117
DOIs	https://doi.org/10.1145/3134421.3134423
State	Published - 27 Oct 2017
Event	2017 Workshop on Recognizing Families In the Wild, RFIW 2017 - Mountain View, United States Duration: 27 Oct 2017 → …

Publication series

Name	RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017

Conference

Conference	2017 Workshop on Recognizing Families In the Wild, RFIW 2017
Country/Territory	United States
City	Mountain View
Period	27/10/17 → …

Bibliographical note

Publisher Copyright:
© 2017 ACM.

Keywords

ACMMM
Artificial intelligence
Big data
Computer vision
Deep Learning
Kin Verification
Kinship recognition
RFIW 2017

Access to Document

10.1145/3134421.3134423

Cite this

Dahan, E., Keller, Y., & Mahpod, S. (2017). Kin-verification model on FIW dataset using multi-set Learning and local features. In RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017 (pp. 31-35). (RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017). Association for Computing Machinery, Inc. https://doi.org/10.1145/3134421.3134423

Dahan, Eran ; Keller, Yosi ; Mahpod, Shahar. / Kin-verification model on FIW dataset using multi-set Learning and local features. RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017. Association for Computing Machinery, Inc, 2017. pp. 31-35 (RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017).

@inproceedings{83639883355740e9a511d62bd11bb65e,

title = "Kin-verification model on FIW dataset using multi-set Learning and local features",

abstract = "Kinship Verification of two or more people has shown to be a complicated problem, though it is widely used in various practical tasks and applications. The areas of the use-cases vary. Among themare applications for homeland security, automatic family recognition, youth and elder matching or predicting and more. We propose using Deep Learning approach to deal with the problem of Kin Verification, such to provide a logical explanation for solving the problem with a novel mechanism for training on the FIW data-set. Our method obtains state-of-the-art for the FIW challenge for the restricted-image setting.1",

keywords = "ACMMM, Artificial intelligence, Big data, Computer vision, Deep Learning, Kin Verification, Kinship recognition, RFIW 2017",

author = "Eran Dahan and Yosi Keller and Shahar Mahpod",

note = "Publisher Copyright: {\textcopyright} 2017 ACM.; 2017 Workshop on Recognizing Families In the Wild, RFIW 2017 ; Conference date: 27-10-2017",

year = "2017",

month = oct,

day = "27",

doi = "10.1145/3134421.3134423",

language = "אנגלית",

series = "RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017",

publisher = "Association for Computing Machinery, Inc",

pages = "31--35",

booktitle = "RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017",

}

Dahan, E, Keller, Y & Mahpod, S 2017, Kin-verification model on FIW dataset using multi-set Learning and local features. in RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017. RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017, Association for Computing Machinery, Inc, pp. 31-35, 2017 Workshop on Recognizing Families In the Wild, RFIW 2017, Mountain View, United States, 27/10/17. https://doi.org/10.1145/3134421.3134423

Kin-verification model on FIW dataset using multi-set Learning and local features. / Dahan, Eran; Keller, Yosi; Mahpod, Shahar.
RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017. Association for Computing Machinery, Inc, 2017. p. 31-35 (RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017).

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

TY - GEN

T1 - Kin-verification model on FIW dataset using multi-set Learning and local features

AU - Dahan, Eran

AU - Keller, Yosi

AU - Mahpod, Shahar

PY - 2017/10/27

Y1 - 2017/10/27

N2 - Kinship Verification of two or more people has shown to be a complicated problem, though it is widely used in various practical tasks and applications. The areas of the use-cases vary. Among themare applications for homeland security, automatic family recognition, youth and elder matching or predicting and more. We propose using Deep Learning approach to deal with the problem of Kin Verification, such to provide a logical explanation for solving the problem with a novel mechanism for training on the FIW data-set. Our method obtains state-of-the-art for the FIW challenge for the restricted-image setting.1

AB - Kinship Verification of two or more people has shown to be a complicated problem, though it is widely used in various practical tasks and applications. The areas of the use-cases vary. Among themare applications for homeland security, automatic family recognition, youth and elder matching or predicting and more. We propose using Deep Learning approach to deal with the problem of Kin Verification, such to provide a logical explanation for solving the problem with a novel mechanism for training on the FIW data-set. Our method obtains state-of-the-art for the FIW challenge for the restricted-image setting.1

KW - ACMMM

KW - Artificial intelligence

KW - Big data

KW - Computer vision

KW - Deep Learning

KW - Kin Verification

KW - Kinship recognition

KW - RFIW 2017

UR - http://www.scopus.com/inward/record.url?scp=85035773023&partnerID=8YFLogxK

U2 - 10.1145/3134421.3134423

DO - 10.1145/3134421.3134423

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85035773023

T3 - RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017

SP - 31

EP - 35

BT - RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017

PB - Association for Computing Machinery, Inc

T2 - 2017 Workshop on Recognizing Families In the Wild, RFIW 2017

Y2 - 27 October 2017

ER -

Dahan E, Keller Y, Mahpod S. Kin-verification model on FIW dataset using multi-set Learning and local features. In RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017. Association for Computing Machinery, Inc. 2017. p. 31-35. (RFIW 2017 - Proceedings of the 2017 Workshop on Recognizing Families In the Wild, co-located with MM 2017). doi: 10.1145/3134421.3134423

Kin-verification model on FIW dataset using multi-set Learning and local features

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this