Machine Learning Systems for Multimodal Affect Recognition [electronic resource] /

Classification and Regression Approaches -- Applications and Affective Corpora -- Modalities and Feature Extraction -- Machine Learning for the Estimation of Affective Dimensions -- Adaptation and Personalization of Classifiers -- Experimental Validation.

Markus Kächele offers a detailed view on the different steps in the affective computing pipeline, ranging from corpus design and recording over annotation and feature extraction to post-processing, classification of individual modalities and fusion in the context of ensemble classifiers. He focuses on multimodal recognition of discrete and continuous emotional and medical states. As such, specifically the peculiarities that arise during annotation and processing of continuous signals are highlighted. Furthermore, methods are presented that allow personalization of datasets and adaptation of classifiers to new situations and persons. Contents Classification and Regression Approaches Applications and Affective Corpora Modalities and Feature Extraction Machine Learning for the Estimation of Affective Dimensions Adaptation and Personalization of Classifiers Experimental Validation Target Groups Lecturers and students of neuroinformatics, artificial intelligence, machine learning, human-machine interaction/affective computing Practitioners in the field of artificial intelligence and human-machine interaction The Author Dr. Markus Kächele is managing partner of Ikara Vision Systems, a spin-off of the German Research Center for Artificial Intelligence (DFKI). He focuses on bridging the gap between research and industrial applications in the fields of deep learning and computer vision.