From Continuous Affective Space to Continuous Expression Space: Non-Verbal Behaviour Recognition and Generation
|Title||From Continuous Affective Space to Continuous Expression Space: Non-Verbal Behaviour Recognition and Generation|
|Publication Type||Conference Paper|
|Year of Publication||2014|
|Authors||Zhong, J., & Cañamero L.|
|Name of Proceedings||Proc. 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-Epirob 2014)|
|Conference Location||Genoa, Italy|
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.