The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans cette lettre, nous proposons une approche de reconnaissance bimodale supervisée des émotions basée sur deux modalités émotionnelles humaines importantes, notamment l'expression faciale et la gestuelle corporelle. Un algorithme de fusion de caractéristiques efficacement supervisé appelé analyse de corrélation canonique multiensemble supervisée (SMCCA) est présenté pour établir la connexion linéaire entre trois ensembles de matrices, qui contiennent la matrice de caractéristiques de deux modalités et leur matrice de catégories concurrentes. Les résultats des tests de reconnaissance bimodale des émotions de la base de données FABO montrent que l'algorithme SMCCA peut obtenir une efficacité meilleure ou considérable que l'algorithme de fusion de caractéristiques non supervisé couvrant l'analyse de corrélation canonique (CCA), l'analyse de corrélation canonique clairsemée (SCCA), l'analyse de corrélation canonique multiensemble (MCCA). ) et ainsi de suite.
Jingjie YAN
Nanjing University of Posts and Telecommunications
Guanming LU
Nanjing University of Posts and Telecommunications
Xiaodong BAI
Nanjing University of Posts and Telecommunications
Haibo LI
Nanjing University of Posts and Telecommunications
Ning SUN
Nanjing University of Posts and Telecommunications
Ruiyu LIANG
Nanjing Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Jingjie YAN, Guanming LU, Xiaodong BAI, Haibo LI, Ning SUN, Ruiyu LIANG, "A Novel Supervised Bimodal Emotion Recognition Approach Based on Facial Expression and Body Gesture" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 11, pp. 2003-2006, November 2018, doi: 10.1587/transfun.E101.A.2003.
Abstract: In this letter, we propose a supervised bimodal emotion recognition approach based on two important human emotion modalities including facial expression and body gesture. A effectively supervised feature fusion algorithms named supervised multiset canonical correlation analysis (SMCCA) is presented to established the linear connection between three sets of matrices, which contain the feature matrix of two modalities and their concurrent category matrix. The test results in the bimodal emotion recognition of the FABO database show that the SMCCA algorithm can get better or considerable efficiency than unsupervised feature fusion algorithm covering canonical correlation analysis (CCA), sparse canonical correlation analysis (SCCA), multiset canonical correlation analysis (MCCA) and so on.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.2003/_p
Copier
@ARTICLE{e101-a_11_2003,
author={Jingjie YAN, Guanming LU, Xiaodong BAI, Haibo LI, Ning SUN, Ruiyu LIANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Novel Supervised Bimodal Emotion Recognition Approach Based on Facial Expression and Body Gesture},
year={2018},
volume={E101-A},
number={11},
pages={2003-2006},
abstract={In this letter, we propose a supervised bimodal emotion recognition approach based on two important human emotion modalities including facial expression and body gesture. A effectively supervised feature fusion algorithms named supervised multiset canonical correlation analysis (SMCCA) is presented to established the linear connection between three sets of matrices, which contain the feature matrix of two modalities and their concurrent category matrix. The test results in the bimodal emotion recognition of the FABO database show that the SMCCA algorithm can get better or considerable efficiency than unsupervised feature fusion algorithm covering canonical correlation analysis (CCA), sparse canonical correlation analysis (SCCA), multiset canonical correlation analysis (MCCA) and so on.},
keywords={},
doi={10.1587/transfun.E101.A.2003},
ISSN={1745-1337},
month={November},}
Copier
TY - JOUR
TI - A Novel Supervised Bimodal Emotion Recognition Approach Based on Facial Expression and Body Gesture
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2003
EP - 2006
AU - Jingjie YAN
AU - Guanming LU
AU - Xiaodong BAI
AU - Haibo LI
AU - Ning SUN
AU - Ruiyu LIANG
PY - 2018
DO - 10.1587/transfun.E101.A.2003
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2018
AB - In this letter, we propose a supervised bimodal emotion recognition approach based on two important human emotion modalities including facial expression and body gesture. A effectively supervised feature fusion algorithms named supervised multiset canonical correlation analysis (SMCCA) is presented to established the linear connection between three sets of matrices, which contain the feature matrix of two modalities and their concurrent category matrix. The test results in the bimodal emotion recognition of the FABO database show that the SMCCA algorithm can get better or considerable efficiency than unsupervised feature fusion algorithm covering canonical correlation analysis (CCA), sparse canonical correlation analysis (SCCA), multiset canonical correlation analysis (MCCA) and so on.
ER -