Decoding affect in videos employing the MEG brain signal

Author

Abadi, Mojtaba Khomami ; Kia, Mohsen ; Subramanian, Ramanathan ; Avesani, Paolo ; Sebe, Nicu

Author_Institution

Univ. of Trento, Trento, Italy

fYear

2013

fDate

22-26 April 2013

Firstpage

1

Lastpage

6

Abstract

This paper presents characterization of affect (valence and arousal) using the Magnetoencephalogram (MEG) brain signal. We attempt single-trial classification of movie and music videos with MEG responses extracted from seven participants. The main findings of this study are that: (i) the MEG signal effectively encodes affective viewer responses, (ii) clip arousal is better predicted than valence employing MEG and (iii) prediction performance is better for movie clips as compared to music videos.

Keywords

magnetoencephalography; medical signal processing; signal classification; video signal processing; MEG brain signal; affect characterization; affective viewer response; arousal; clip arousal; magnetoencephalogram; movie; music video; prediction performance; single-trial classification; valence; Discrete cosine transforms; Feature extraction; Magnetic recording; Magnetic resonance imaging; Motion pictures; Time-frequency analysis; Videos;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Face and Gesture Recognition (FG), 2013 10th IEEE International Conference and Workshops on

Conference_Location

Shanghai

Print_ISBN

978-1-4673-5545-2

Electronic_ISBN

978-1-4673-5544-5

Type

conf

DOI

10.1109/FG.2013.6553809

Filename

6553809