From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation

Junpei Zhong; Lola Canamero

doi:10.1109/DEVLRN.2014.6982957

From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation

Junpei Zhong, Lola Canamero

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.

Original language	English
Title of host publication	IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	75-80
Number of pages	6
ISBN (Electronic)	9781479975402
DOIs	https://doi.org/10.1109/DEVLRN.2014.6982957
Publication status	Published - 2014 Dec 11
Externally published	Yes
Event	4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014 - Genoa Duration: 2014 Oct 13 → 2014 Oct 16

Other

Other	4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014
City	Genoa
Period	14/10/13 → 14/10/16

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition

Access to Document

10.1109/DEVLRN.2014.6982957

Cite this

Zhong, J., & Canamero, L. (2014). From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation. In IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (pp. 75-80). [6982957] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEVLRN.2014.6982957

From continuous affective space to continuous expression space : Non-verbal behaviour recognition and generation. / Zhong, Junpei; Canamero, Lola.

IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc., 2014. p. 75-80 6982957.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhong, J & Canamero, L 2014, From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation. in IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics., 6982957, Institute of Electrical and Electronics Engineers Inc., pp. 75-80, 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014, Genoa, 14/10/13. https://doi.org/10.1109/DEVLRN.2014.6982957

Zhong J, Canamero L. From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation. In IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Institute of Electrical and Electronics Engineers Inc. 2014. p. 75-80. 6982957 https://doi.org/10.1109/DEVLRN.2014.6982957

@inproceedings{03b94d6d5bbd4392ae52d4991b4daa6b,

title = "From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation",

abstract = "In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.",

author = "Junpei Zhong and Lola Canamero",

year = "2014",

month = dec,

day = "11",

doi = "10.1109/DEVLRN.2014.6982957",

language = "English",

pages = "75--80",

booktitle = "IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014 ; Conference date: 13-10-2014 Through 16-10-2014",

}

TY - GEN

T1 - From continuous affective space to continuous expression space

T2 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE ICDL-EPIROB 2014

AU - Zhong, Junpei

AU - Canamero, Lola

PY - 2014/12/11

Y1 - 2014/12/11

N2 - In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.

AB - In this research, a recurrent neural network with parametric bias (RNNPB) was adopted to construct a continuous expression space from emotion caused human behaviours. It made use of the short-term memory ability of the recurrent weights to store spatio-temporal sequences features, while the attached parametric bias units were trained in a self-organizing way and represented as a low-dimensional expression space to capture these non-linear features of the sequences. Three demonstrations were given: training and recognition performances were examined in computer simulations, while the network generated both trained and novel movements were shown in a three-dimensional avatar demonstrations.

UR - http://www.scopus.com/inward/record.url?scp=84920876995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920876995&partnerID=8YFLogxK

U2 - 10.1109/DEVLRN.2014.6982957

DO - 10.1109/DEVLRN.2014.6982957

M3 - Conference contribution

AN - SCOPUS:84920876995

SP - 75

EP - 80

BT - IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 October 2014 through 16 October 2014

ER -

From continuous affective space to continuous expression space: Non-verbal behaviour recognition and generation

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this