@Article{AjianLiu2022,
author="Ajian Liu
and Chenxu Zhao
and Zitong Yu
and Jun Wan
and Anyang Su
and Xing Liu
and Zichang Tan
and Sergio Escalera
and Junliang Xing
and Yanyan Liang
and Guodong Guo
and Zhen Lei
and Stan Z. Li
and Shenshen Du",
title="Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection",
journal="IEEE Transactions on Information Forensics and Security",
year="2022",
publisher="IEEE",
volume="17",
pages="2497--2507",
abstract="Face presentation attack detection (PAD) is essential to secure face recognition systems primarily from high-fidelity mask attacks. Most existing 3D mask PAD benchmarks suffer from several drawbacks: 1) a limited number of mask identities, types of sensors, and a total number of videos; 2) low-fidelity quality of facial masks. Basic deep models and remote photoplethysmography (rPPG) methods achieved acceptable performance on these benchmarks but still far from the needs of practical scenarios. To bridge the gap to real-world applications, we introduce a large-scale Hi gh- Fi delity Mask dataset, namely HiFiMask . Specifically, a total amount of 54,600 videos are recorded from 75 subjects with 225 realistic masks by 7 new kinds of sensors. Along with the dataset, we propose a novel C ontrastive C ontext-aware L earning (CCL) framework. CCL is a new training methodology for supervised PAD tasks, which is able to learn by leveraging rich contexts accurately (e.g., subjects, mask material and lighting) among pairs of live faces and high-fidelity mask attacks. Extensive experimental evaluations on HiFiMask and three additional 3D mask datasets demonstrate the effectiveness of our method. The codes and dataset will be released soon.",
optnote="HuPBA",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3778), last updated on Tue, 25 Apr 2023 10:30:56 +0200",
doi="10.1109/TIFS.2022.3188149"
}