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 | |
| 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 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition
Cite this
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
}
TY - GEN
T1 - From continuous affective space to continuous expression space
T2 - Non-verbal behaviour recognition and generation
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.
ER -