Z
Zezheng Wang
Researcher at Tianjin University
Publications - 30
Citations - 1039
Zezheng Wang is an academic researcher from Tianjin University. The author has contributed to research in topics: Spoofing attack & Facial recognition system. The author has an hindex of 11, co-authored 29 publications receiving 437 citations. Previous affiliations of Zezheng Wang include State Administration of Cultural Heritage & University of Oulu.
Papers
More filters
Proceedings ArticleDOI
Searching Central Difference Convolutional Networks for Face Anti-Spoofing
TL;DR: Yu et al. as discussed by the authors proposed a frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information.
Proceedings ArticleDOI
Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing
TL;DR: A new approach to detect presentation attacks from multiple frames based on two insights, able to capture discriminative details via Residual Spatial Gradient Block (RSGB) and encode spatio-temporal information from Spatio-Temporal Propagation Module (STPM) efficiently.
Proceedings ArticleDOI
A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing
Shifeng Zhang,Xiaobo Wang,Ajian Liu,Chenxu Zhao,Jun Wan,Sergio Escalera,Hailin Shi,Zezheng Wang,Stan Z. Li +8 more
TL;DR: CASIA-SURF as mentioned in this paper is a large-scale multi-modal dataset for face anti-spoofing, which consists of 1,000 subjects with 21,000 videos and each sample has three modalities (i.e., RGB, depth and IR).
Journal ArticleDOI
Learning meta model for zero- and few-shot face anti-spoofing
Yunxiao Qin,Chenxu Zhao,Xiangyu Zhu,Zezheng Wang,Zitong Yu,Tianyu Fu,Feng Zhou,Jingping Shi,Zhen Lei +8 more
TL;DR: A novel Adaptive Inner-update Meta Face Anti-Spoofing (AIM-FAS) method, which trains a meta-learner focusing on the task of detecting unseen spoofing types by learning from predefined living and spoofing faces and a few examples of new attacks.
Posted Content
Exploiting temporal and depth information for multi-frame face anti-spoofing.
TL;DR: A new method to estimate depth information from multiple RGB frames is developed and a depth-supervised architecture which can efficiently encodes spatiotemporal information for presentation attack detection is proposed.