Title: Neural networks for multimodal emotion recognition

Abstract: Research activities in human-computer interaction increasingly addressed the aspect of integrating emotional intelligence into the overall system, and therefore the recognition of human emotions becomes important in such applications. Human emotions are expressed through various kinds of modalities such as voice, facial expressions, hand/body gestures or bio-physiological patterns, and therefore the classification of human emotions should be considered as a multi-modal pattern recognition and machine learning problem. In this talk, we propose artificial neural networks for the task of information fusion in multimodal affect classification.

About the speaker: Friedhelm Schwenker is Privatdozent of Computer Science at the Institute of Neural Information Processing, Ulm University, Germany and Dr. rer. nat. (Mathematics: Approximation Theory), University of Osnabrück. He was Technical Committee Chair of IAPR TC3 on Artificial Neural Networks in Pattern Recognition from 2010 to 2014; since 2016, he is the founder and Technical Committee Chair of IAPR TC9 on Pattern recognition in Human Computer Interaction. Friedhelm has edited 19 Special Issues, Books and Proceedings, and is the Author of 200+ Papers in journals, conferences and workshops. His research interests include neural networks, machine learning, pattern recognition, affective computing.

For more Information, see Friedhelm’s Homepage https://www.uni-ulm.de/in/neuroinformatik/institut/hidden/f-schwenker/