4DFAB: A Large Scale 4D Facial Expression Database for Biometric Applications

Shiyang Cheng; Irene Kotsia; Maja  Pantic; Stefanos Zafeiriou

4DFAB: A Large Scale 4D Facial Expression Database for Biometric Applications

Shiyang Cheng, Irene Kotsia, Maja Pantic, Stefanos Zafeiriou

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

82 Downloads (Pure)

Abstract

The progress we are currently witnessing in many computer vision applications, including automatic face analysis, would not be made possible without tremendous efforts in collecting and annotating large scale visual databases. To this end, we propose 4DFAB, a new large scale database of dynamic high-resolution 3D faces (over 1,800,000 3D meshes). 4DFAB contains recordings of 180 subjects captured in four different sessions spanning over a five-year period. It contains 4D videos of subjects displaying both spontaneous and posed facial behaviours. The database can be used for both face and facial expression recognition, as well as behavioural biometrics. It can also be used to learn very powerful blendshapes for parametrising facial behaviour. In this paper, we conduct several experiments and demonstrate the usefulness of the database for various applications. The database will be made publicly available for research purposes.

Original language	English
Title of host publication	30th IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2017
Subtitle of host publication	21-26 July 2016, Honolulu, Hawaii : proceedings
Editors	Rama Chellappa, Zhengyou Zhang, Anthony Hoogs
Publisher	IEEE
Number of pages	12
ISBN (Electronic)	978-1-5386-0457-1
ISBN (Print)	978-1-5386-0458-8
Publication status	Published - 5 Dec 2017
Event	30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Hawaii Convention Center, Honolulu, United States Duration: 21 Jul 2017 → 26 Jul 2017 Conference number: 30 http://cvpr2017.thecvf.com/

Conference

Conference	30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Abbreviated title	CVPR
Country/Territory	United States
City	Honolulu
Period	21/07/17 → 26/07/17
Internet address	http://cvpr2017.thecvf.com/

Access to Document

4DFAB A Large Scale 4D Facial Expression Database for Biometric ApplicationsAccepted author version, 5.4 MB

https://arxiv.org/abs/1712.01443

Cite this

@inproceedings{b5448544c91d4031971009d60f4e4644,

title = "4DFAB: A Large Scale 4D Facial Expression Database for Biometric Applications",

abstract = "The progress we are currently witnessing in many computer vision applications, including automatic face analysis, would not be made possible without tremendous efforts in collecting and annotating large scale visual databases. To this end, we propose 4DFAB, a new large scale database of dynamic high-resolution 3D faces (over 1,800,000 3D meshes). 4DFAB contains recordings of 180 subjects captured in four different sessions spanning over a five-year period. It contains 4D videos of subjects displaying both spontaneous and posed facial behaviours. The database can be used for both face and facial expression recognition, as well as behavioural biometrics. It can also be used to learn very powerful blendshapes for parametrising facial behaviour. In this paper, we conduct several experiments and demonstrate the usefulness of the database for various applications. The database will be made publicly available for research purposes.",

author = "Shiyang Cheng and Irene Kotsia and Maja Pantic and Stefanos Zafeiriou",

note = "12 pages; 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, CVPR ; Conference date: 21-07-2017 Through 26-07-2017",

year = "2017",

month = dec,

day = "5",

language = "English",

isbn = "978-1-5386-0458-8",

editor = "Rama Chellappa and Zhengyou Zhang and Anthony Hoogs",

booktitle = "30th IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2017",

publisher = "IEEE",

address = "United States",

url = "http://cvpr2017.thecvf.com/",

}

Cheng, S, Kotsia, I, Pantic, M & Zafeiriou, S 2017, 4DFAB: A Large Scale 4D Facial Expression Database for Biometric Applications. in R Chellappa, Z Zhang & A Hoogs (eds), 30th IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2017: 21-26 July 2016, Honolulu, Hawaii : proceedings. IEEE, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, Hawaii, United States, 21/07/17. <https://arxiv.org/abs/1712.01443>

4DFAB: A Large Scale 4D Facial Expression Database for Biometric Applications. / Cheng, Shiyang; Kotsia, Irene; Pantic, Maja et al.
30th IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2017: 21-26 July 2016, Honolulu, Hawaii : proceedings. ed. / Rama Chellappa; Zhengyou Zhang; Anthony Hoogs. IEEE, 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - 4DFAB

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

AU - Cheng, Shiyang

AU - Kotsia, Irene

AU - Pantic, Maja

AU - Zafeiriou, Stefanos

N1 - Conference code: 30

PY - 2017/12/5

Y1 - 2017/12/5

N2 - The progress we are currently witnessing in many computer vision applications, including automatic face analysis, would not be made possible without tremendous efforts in collecting and annotating large scale visual databases. To this end, we propose 4DFAB, a new large scale database of dynamic high-resolution 3D faces (over 1,800,000 3D meshes). 4DFAB contains recordings of 180 subjects captured in four different sessions spanning over a five-year period. It contains 4D videos of subjects displaying both spontaneous and posed facial behaviours. The database can be used for both face and facial expression recognition, as well as behavioural biometrics. It can also be used to learn very powerful blendshapes for parametrising facial behaviour. In this paper, we conduct several experiments and demonstrate the usefulness of the database for various applications. The database will be made publicly available for research purposes.

AB - The progress we are currently witnessing in many computer vision applications, including automatic face analysis, would not be made possible without tremendous efforts in collecting and annotating large scale visual databases. To this end, we propose 4DFAB, a new large scale database of dynamic high-resolution 3D faces (over 1,800,000 3D meshes). 4DFAB contains recordings of 180 subjects captured in four different sessions spanning over a five-year period. It contains 4D videos of subjects displaying both spontaneous and posed facial behaviours. The database can be used for both face and facial expression recognition, as well as behavioural biometrics. It can also be used to learn very powerful blendshapes for parametrising facial behaviour. In this paper, we conduct several experiments and demonstrate the usefulness of the database for various applications. The database will be made publicly available for research purposes.

M3 - Conference contribution

SN - 978-1-5386-0458-8

BT - 30th IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2017

A2 - Chellappa, Rama

A2 - Zhang, Zhengyou

A2 - Hoogs, Anthony

PB - IEEE

Y2 - 21 July 2017 through 26 July 2017

ER -