Affect Recognition from Face and Body: Early Fusion vs. Late Fusion

UTSePress Research/Manakin Repository

Search UTSePress Research

Advanced Search


My Account

Show simple item record Gunes, Hatice en_US Piccardi, Massimo en_US
dc.contributor.editor Jamshidi, M; Anderson, G; Tuntsel, R en_US 2009-11-09T05:36:21Z 2009-11-09T05:36:21Z 2005 en_US
dc.identifier 2005003128 en_US
dc.identifier.citation Gunes Hatice and Piccardi Massimo 2005, 'Affect Recognition from Face and Body: Early Fusion vs. Late Fusion', IEEE, Piscataway, USA, pp. 3437-3443. en_US
dc.identifier.issn 0-7803-9298-x en_US
dc.identifier.other E1 en_US
dc.description.abstract This paper presents an approach to automatic visual emotion recognition from two modalities: face and body. Firstly, individual classifiers are trained from individual modalities. Secondly, we fuse facial expression and affective body gesture information first at a feature-level, in which the data from both modalities are combined before classification, and later at a decision-level, in which we integrate the outputs of the monomodal systems by the use of suitable criteria. We then evaluate these two fusion approaches, in terms of performance over monomodal emotion recognition based on facial expression modality only. In the experiments performed the emotion classification using the two modalities achieved a better recognition accuracy outperforming the classification using the individual facial modality. Moreover, fusion at the feature-level proved better recognition than fusion at the decision-level. en_US
dc.publisher IEEE en_US
dc.relation.hasversion Accepted manuscript version
dc.relation.isbasedon en_US
dc.title Affect Recognition from Face and Body: Early Fusion vs. Late Fusion en_US
dc.parent Proceedings of IEEE Systems, Man and Cyberntetics Conference 2005 en_US
dc.journal.number en_US
dc.publocation Piscataway, USA en_US
dc.identifier.startpage 3437 en_US
dc.identifier.endpage 3443 en_US FEIT.School of Systems, Management and Leadership en_US
dc.conference Verified OK en_US
dc.conference.location Hawaii, USA en_US
dc.for 080602 en_US
dc.personcode 034144 en_US
dc.personcode 020073 en_US
dc.percentage 100 en_US Computer-Human Interaction en_US
dc.classification.type FOR-08 en_US
dc.custom IEEE Conference on Systems, Man and Cybernetics en_US 20051010 en_US
dc.location.activity Hawaii, USA en_US
dc.description.keywords human computer interface, affective state analysis, emotion recognition en_US
dc.staffid 020073 en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record