Taihong Xiao

Taihong Xiao

Auto-generated profile, based on publicly available information

Taihong Xiao

University of California, Merced, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
TXTaihong Xiao
Taihong Xiao
JHJiapeng Hong
Jiapeng Hong
Jinwen MaJinwen Ma
Jinwen Ma

24 March 2022 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
TXTaihong Xiao
Taihong Xiao
SLSifei Liu
Sifei Liu
SMShalini De Mello
Shalini De Mello
ZYZhiding Yu
Zhiding Yu
JKJan Kautz
Jan Kautz
MYMing Yang
Ming Yang

5 November 2020
Verified
Book Chapter
Closed access
PDF file
TXTaihong Xiao
Taihong Xiao
JYJinwei Yuan
Jinwei Yuan
DSDeqing Sun
Deqing Sun
QWQifei Wang
Qifei Wang
XZXin-Yu Zhang
Xin-Yu Zhang
MYMing Yang
Ming Yang

25 October 2023 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ZLZhiwei Lin
Zhiwei Lin
TLTingting Liang
Tingting Liang
TXTaihong Xiao
Taihong Xiao
YWYongtao Wang
Yongtao Wang
MYMing Yang
Ming Yang

13 April 2022 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
TXTaihong Xiao
Taihong Xiao
SLSifei Liu
Sifei Liu
SMShalini De Mello
Shalini De Mello
ZYZhiding Yu
Zhiding Yu
JKJan Kautz
Jan Kautz
MYMing Yang
Ming Yang

28 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
HHHsin-Ping Huang
Hsin-Ping Huang
DSDeqing Sun
Deqing Sun
YLYaojie Liu
Yaojie Liu
WCWen-Sheng Chu
Wen-Sheng Chu
TXTaihong Xiao
Taihong Xiao
MYMing Yang
Ming Yang
While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance. In this paper, we present adaptive vision transformers (ViT) for robust cross-domain face antispoofing. Specifically, we adopt ViT as a backbone to exploit its strength to account for long-range dependencies among pixels. We further introduce the ensemble adapters module and feature-wise transformation layers in the ViT to adapt to different domains for robust performance with a few samples. Experiments on several benchmark datasets show that the proposed models achieve both robust and competitive performance against the state-of-the-art methods for cross-domain face anti-spoofing using a few samples.