3D High-Fidelity Mask Face Presentation Attack Detection Challenge

Ajian Liu; Chenxu Zhao; Zitong Yu; Anyang Su; Xing Liu; Zijian Kong; Jun Wan; Sergio Escalera; Hugo Jair Escalante; Zhen Lei; Guodong Guo

doi:10.1109/ICCVW54120.2021.00096

3D High-Fidelity Mask Face Presentation Attack Detection Challenge

Ajian Liu, Chenxu Zhao, Zitong Yu, Anyang Su, Xing Liu, Zijian Kong, Jun Wan^*, Sergio Escalera, Hugo Jair Escalante, Zhen Lei, Guodong Guo

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

17 Citations (Scopus)

Abstract

The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers. To facilitate the study of the algorithms, a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask) has been collected. Specifically, it consists of a total amount of 54, 600 videos which are recorded from 75 subjects with 225 realistic masks under 7 new kinds of sensors [21]. Based on this dataset and Protocol 3 which evaluates both the discrimination and generalization ability of the algorithm under the open set scenarios, we organized a 3D High-Fidelity Mask Face Presentation Attack Detection Challenge to boost the research of 3D mask-based attack detection. It attracted 195 teams for the development phase with a total of 18 teams qualifying for the final round. All the results were verified and re-run by the organizing team, and the results were used for the final ranking. This paper presents an overview of the challenge, including the introduction of the dataset used, the definition of the protocol, the calculation of the evaluation criteria, and the summary and publication of the competition results. Finally, we focus on introducing and analyzing the top ranking algorithms, the conclusion summary, and the research ideas for mask attack detection provided by this competition.

Original language	English
Title of host publication	Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Number of pages	10
Publisher	IEEE Signal Processing Society
Publication date	2021
Pages	814-823
ISBN (Electronic)	9781665401913
DOIs	https://doi.org/10.1109/ICCVW54120.2021.00096
Publication status	Published - 2021
Externally published	Yes
Event	18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 - Virtual, Online, Canada Duration: 11 Oct 2021 → 17 Oct 2021

Conference

Conference	18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Country/Territory	Canada
City	Virtual, Online
Period	11/10/2021 → 17/10/2021
Sponsor	CVF, IEEE

Series	Proceedings of the IEEE International Conference on Computer Vision
Volume	2021-October
ISSN	1550-5499

Bibliographical note

Funding Information:
This work was supported by the Chinese National Natural Science Foundation Projects #61961160704, #61876179, the External cooperation key project of Chinese Academy Sciences # 173211KYSB20200002, the Key Project of the General Logistics Department Grant No.AWS17J001, Science and Technology Development Fund of Macau (No. 0010/2019/AFJ, 0008/2019/A1, 0025/2019/AKP, 0019/2018/ASC), by the Spanish project PID2019-105093GB-I00 (MINECO/FEDER, UE), and by ICREA under the ICREA Academia programme.

Publisher Copyright:
© 2021 IEEE.

Access to Document

10.1109/ICCVW54120.2021.00096

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Liu, A., Zhao, C., Yu, Z., Su, A., Liu, X., Kong, Z., Wan, J., Escalera, S., Escalante, H. J., Lei, Z., & Guo, G. (2021). 3D High-Fidelity Mask Face Presentation Attack Detection Challenge. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 (pp. 814-823). IEEE Signal Processing Society. https://doi.org/10.1109/ICCVW54120.2021.00096

@inproceedings{1637c279ccf94b8b90cd44b8ff0f0ea4,

title = "3D High-Fidelity Mask Face Presentation Attack Detection Challenge",

abstract = "The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers. To facilitate the study of the algorithms, a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask) has been collected. Specifically, it consists of a total amount of 54, 600 videos which are recorded from 75 subjects with 225 realistic masks under 7 new kinds of sensors [21]. Based on this dataset and Protocol 3 which evaluates both the discrimination and generalization ability of the algorithm under the open set scenarios, we organized a 3D High-Fidelity Mask Face Presentation Attack Detection Challenge to boost the research of 3D mask-based attack detection. It attracted 195 teams for the development phase with a total of 18 teams qualifying for the final round. All the results were verified and re-run by the organizing team, and the results were used for the final ranking. This paper presents an overview of the challenge, including the introduction of the dataset used, the definition of the protocol, the calculation of the evaluation criteria, and the summary and publication of the competition results. Finally, we focus on introducing and analyzing the top ranking algorithms, the conclusion summary, and the research ideas for mask attack detection provided by this competition. ",

author = "Ajian Liu and Chenxu Zhao and Zitong Yu and Anyang Su and Xing Liu and Zijian Kong and Jun Wan and Sergio Escalera and Escalante, {Hugo Jair} and Zhen Lei and Guodong Guo",

note = "Funding Information: This work was supported by the Chinese National Natural Science Foundation Projects #61961160704, #61876179, the External cooperation key project of Chinese Academy Sciences # 173211KYSB20200002, the Key Project of the General Logistics Department Grant No.AWS17J001, Science and Technology Development Fund of Macau (No. 0010/2019/AFJ, 0008/2019/A1, 0025/2019/AKP, 0019/2018/ASC), by the Spanish project PID2019-105093GB-I00 (MINECO/FEDER, UE), and by ICREA under the ICREA Academia programme. Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 ; Conference date: 11-10-2021 Through 17-10-2021",

year = "2021",

doi = "10.1109/ICCVW54120.2021.00096",

language = "English",

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

pages = "814--823",

booktitle = "Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021",

publisher = "IEEE Signal Processing Society",

address = "United States",

}

Liu, A, Zhao, C, Yu, Z, Su, A, Liu, X, Kong, Z, Wan, J, Escalera, S, Escalante, HJ, Lei, Z & Guo, G 2021, 3D High-Fidelity Mask Face Presentation Attack Detection Challenge. in Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. IEEE Signal Processing Society, Proceedings of the IEEE International Conference on Computer Vision, vol. 2021-October, pp. 814-823, 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Virtual, Online, Canada, 11/10/2021. https://doi.org/10.1109/ICCVW54120.2021.00096

3D High-Fidelity Mask Face Presentation Attack Detection Challenge. / Liu, Ajian; Zhao, Chenxu; Yu, Zitong et al.
Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. IEEE Signal Processing Society, 2021. p. 814-823 (Proceedings of the IEEE International Conference on Computer Vision, Vol. 2021-October).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - 3D High-Fidelity Mask Face Presentation Attack Detection Challenge

AU - Liu, Ajian

AU - Zhao, Chenxu

AU - Yu, Zitong

AU - Su, Anyang

AU - Liu, Xing

AU - Kong, Zijian

AU - Wan, Jun

AU - Escalera, Sergio

AU - Escalante, Hugo Jair

AU - Lei, Zhen

AU - Guo, Guodong

N1 - Funding Information: This work was supported by the Chinese National Natural Science Foundation Projects #61961160704, #61876179, the External cooperation key project of Chinese Academy Sciences # 173211KYSB20200002, the Key Project of the General Logistics Department Grant No.AWS17J001, Science and Technology Development Fund of Macau (No. 0010/2019/AFJ, 0008/2019/A1, 0025/2019/AKP, 0019/2018/ASC), by the Spanish project PID2019-105093GB-I00 (MINECO/FEDER, UE), and by ICREA under the ICREA Academia programme. Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers. To facilitate the study of the algorithms, a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask) has been collected. Specifically, it consists of a total amount of 54, 600 videos which are recorded from 75 subjects with 225 realistic masks under 7 new kinds of sensors [21]. Based on this dataset and Protocol 3 which evaluates both the discrimination and generalization ability of the algorithm under the open set scenarios, we organized a 3D High-Fidelity Mask Face Presentation Attack Detection Challenge to boost the research of 3D mask-based attack detection. It attracted 195 teams for the development phase with a total of 18 teams qualifying for the final round. All the results were verified and re-run by the organizing team, and the results were used for the final ranking. This paper presents an overview of the challenge, including the introduction of the dataset used, the definition of the protocol, the calculation of the evaluation criteria, and the summary and publication of the competition results. Finally, we focus on introducing and analyzing the top ranking algorithms, the conclusion summary, and the research ideas for mask attack detection provided by this competition.

AB - The threat of 3D masks to face recognition systems is increasingly serious and has been widely concerned by researchers. To facilitate the study of the algorithms, a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask) has been collected. Specifically, it consists of a total amount of 54, 600 videos which are recorded from 75 subjects with 225 realistic masks under 7 new kinds of sensors [21]. Based on this dataset and Protocol 3 which evaluates both the discrimination and generalization ability of the algorithm under the open set scenarios, we organized a 3D High-Fidelity Mask Face Presentation Attack Detection Challenge to boost the research of 3D mask-based attack detection. It attracted 195 teams for the development phase with a total of 18 teams qualifying for the final round. All the results were verified and re-run by the organizing team, and the results were used for the final ranking. This paper presents an overview of the challenge, including the introduction of the dataset used, the definition of the protocol, the calculation of the evaluation criteria, and the summary and publication of the competition results. Finally, we focus on introducing and analyzing the top ranking algorithms, the conclusion summary, and the research ideas for mask attack detection provided by this competition.

UR - http://www.scopus.com/inward/record.url?scp=85121779975&partnerID=8YFLogxK

U2 - 10.1109/ICCVW54120.2021.00096

DO - 10.1109/ICCVW54120.2021.00096

M3 - Article in proceeding

AN - SCOPUS:85121779975

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 814

EP - 823

BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021

PB - IEEE Signal Processing Society

T2 - 18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021

Y2 - 11 October 2021 through 17 October 2021

ER -

Liu A, Zhao C, Yu Z, Su A, Liu X, Kong Z et al. 3D High-Fidelity Mask Face Presentation Attack Detection Challenge. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. IEEE Signal Processing Society. 2021. p. 814-823. (Proceedings of the IEEE International Conference on Computer Vision, Vol. 2021-October). doi: 10.1109/ICCVW54120.2021.00096

3D High-Fidelity Mask Face Presentation Attack Detection Challenge

Abstract

Conference

Bibliographical note

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this