TY - CONF T1 - From Continuous Affective Space to Continuous Expression Space: Non-Verbal Behaviour Recognition and Generation T2 - Proc. 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-Epirob 2014) Y1 - 2014 A1 - Junpei Zhong A1 - Lola CaƱamero 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. JF - Proc. 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-Epirob 2014) PB - IEEE CY - Genoa, Italy UR - http://ieeexplore.ieee.org/document/6982957/ N1 - Download ER -