Graduate School and Research Center in Digital Sciences

Evidence theory based multimodal emotion recognition

Paleari, Marco;Benmokhtar, Rachid;Huet, Benoit

MMM 2009, 15th International MultiMedia Modeling Conference, January 7-9, 2009, Sophia Antipolis, France

      Automatic recognition of human affective states is still a largely unexplored and challenging topic. Even more issues arise when dealing with variable quality of the inputs or aiming for real-time, unconstrained, and person independent scenarios. In this paper, we explore audio-visual multimodal emotion recognition. We present SAMMI, a framework designed to extract real-time emotion appraisals from non-prototypical, person independent, facial expressions and vocal prosody. Different probabilistic method for fusion are compared and evaluated with a novel fusion technique called NNET. Results shows that NNET can improve the recognition score (CR+) of about 19% and the mean average precision of about 30% with respect to the best unimodal system.

Document Doi Bibtex

Title:Evidence theory based multimodal emotion recognition
Type:Conference
Language:English
City:Sophia Antipolis
Country:FRANCE
Date:
Department:Data Science
Eurecom ref:2596
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in MMM 2009, 15th International MultiMedia Modeling Conference, January 7-9, 2009, Sophia Antipolis, France and is available at : http://dx.doi.org/10.1007/978-3-540-92892-8_44
Bibtex: @inproceedings{EURECOM+2596, doi = {http://dx.doi.org/10.1007/978-3-540-92892-8_44}, year = {2009}, title = {{E}vidence theory based multimodal emotion recognition}, author = {{P}aleari, {M}arco and {B}enmokhtar, {R}achid and {H}uet, {B}enoit}, booktitle = {{MMM} 2009, 15th {I}nternational {M}ulti{M}edia {M}odeling {C}onference, {J}anuary 7-9, 2009, {S}ophia {A}ntipolis, {F}rance}, address = {{S}ophia {A}ntipolis, {FRANCE}}, month = {01}, url = {http://www.eurecom.fr/publication/2596} }
See also: