PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer

Approved

Classifications

MinEdu publication type
A1 Journal article (peer-reviewed)
Definition
Article
Target group
Scientific
Peer reviewed
Peer-reviewed
Article type
Journal article
Host publication type
Journal

Authors of the publication

Number of authors
8
Authors
Yu, Zitong; Shen, Yuming; Shi, Jingang; Zhao, Hengshuang; Cui, Yawen; Zhang, Jiehua; Torr, Philip; Zhao, Guoying

Publication channel information

Title of journal/series
International journal of computer vision
ISSN (print)
0920-5691
ISSN (electronic)
1573-1405
ISSN (linking)
0920-5691
Publisher
Springer
Publication forum ID
58342
Publication forum level
3
Country of publication
United States
Internationality
Yes

Detailed publication information

Publication year
2023
Bibliographical publication year
2023
Reporting year
2023
Journal/series volume number
131
Page numbers
1307-1330
DOI
10.1007/s11263-023-01758-1
Language of publication
English

Co-publication information

International co-publication
Yes
Co-publication with a company
No

Availability

Link to self-archived version
http://urn.fi/urn:nbn:fi-fe2023040334642

Classification and additional information

MinEdu field of science classification
113 Computer and information sciences
Keywords
RPPG; Temporal difference transformer; SlowFast; Cross-attention; Periodic-attention

Funding information

Funding information in the publication
This work was supported by the Academy of Finland (Academy Professor project EmotionAI with grant numbers 336116 and 345122, and ICT2023 project with grant number 345948), the National Natural Science Foundation of China (Grant No. 62002283), HKU Startup Fund, HKU Seed Fund for Basic Research, and the EPSRC grant: Turing AI Fellowship: EP/W002981/1, EPSRC/MURI grant EP/N019474/1. We would also like to thank the Royal Academy of Engineering and FiveAI.
Funders
Funder
Research Council of Finland (former Academy of Finland)
Name of funding
-
Funding decision
-

Infrastructure information

Infrastructure information in the publication
The authors wish to acknowledge CSC-IT Center for Science, Finland, for computational resources.

Source database ID

WoS ID
WOS:000933348800002
Scopus ID
2-s2.0-85148065784