2020 Face Anti-spoofing (Presentation Attack Detection) Challenge at CVPR

Introduction

In this challenge, we will release a largest cross-ethnicity dataset CASIA-SURF CeFA for face antispoofing (please refer to [1]). It includes four protocols. But for this challenge, we have two tracks and only use protocol 4 (Cross-ethnicity & PAI) .

• Track 1 (Multi-modal data): It uses the protocol 4 (Cross-ethnicity & PAI) in [1]. Participates can use multiply modalities, such as RGB, depth and IR data. Any extra data or pretrained model cannot be used in track 1 (link).
• Track 2 (Single RGB modal data): It uses the protocol protocol 4 (Cross-ethnicity & PAI) in [1]. But participates are only permitted to use the single RGB modality. Any extra data or pretrained model cannot be used in track 2 (link).

Dataset Application [link]

Full Schedule of Workshop@CVPR2020

Challenge Results

Organizers

• Jun Wan (万军), NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA), China, jun.wan@ia.ac.cn
• Ajian Liu, Macau University of Science and Technology (M.U.S.T.), Macau, China, 1809853nii30001@student.must.edu.mo
• Sergio Escalera, Computer Vision Center (UAB) and University of Barcelona, Spain, sergio@maia.ub.es
• Hugo Jair Escalante, INAOE, ChaLearn, Mexico, hugojair@inaoep.mx
• Isabelle Guyon, Université Paris-Saclay, France and ChaLearn, Berkeley, California, USA, guyon@chalearn.org
• Guodong Guo, IDL, Baidu Research, China, guoguodong01@baidu.com
• Shaopeng Tang, Beijing Surfing Technology Ltd, shaopeng@surfingtech.cn

Sponsor

• Baidu (the exclusive sponsorship)

Ref:

[1]Ajian Liu, Zichang Tan, Xuan Li, Jun Wan*, Sergio Escalera, Guodong Guo, Stan Z. Li, " Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing ", arxiv, 2019.

You can find additional information about this challenge here.