Analyzing group-level emotion with global alignment kernel based approach

Xiaohua Huang, Abhinav Dhall, Roland Goecke, Matti K. Pietikainen, Guoying Zhao

Research output: Contribution to journalArticle

Abstract

From the perspective of social science, understanding group emotion has become increasingly important for teams to considerably accomplish organizational work. Currently, automatically analyzing the perceived affect of a group of people has been received increasingly interest in affective computing community. The variability in group size makes difficulty for group-level emotion recognition to straightforwardly measure the feature distance of two group-level images. To alleviate this problem, this paper aims to design a new method to effectively analyze the group behavior from a group-level image. Motivated by time-series kernel approaches explored in dynamic facial expression classification, this paper mainly concentrates on global alignment kernel and design support vector machine with the combined global alignment kernels (SVM-CGAK) to better recognize group-level emotion. Intensive experiments are conducted on three challenging group-level emotion databases. The experimental results demonstrate that the proposed approach achieves promising performance for group-level emotion recognition compared with the recent state-of-the-art methods.

Original languageEnglish
Number of pages16
JournalIEEE Transactions on Affective Computing
DOIs
Publication statusPublished - 14 Nov 2019

Fingerprint

Social sciences
Support vector machines
Time series
Experiments

Cite this

Huang, Xiaohua ; Dhall, Abhinav ; Goecke, Roland ; Pietikainen, Matti K. ; Zhao, Guoying. / Analyzing group-level emotion with global alignment kernel based approach. In: IEEE Transactions on Affective Computing. 2019.
@article{7648b51af0a0460bb9979445bb40c607,
title = "Analyzing group-level emotion with global alignment kernel based approach",
abstract = "From the perspective of social science, understanding group emotion has become increasingly important for teams to considerably accomplish organizational work. Currently, automatically analyzing the perceived affect of a group of people has been received increasingly interest in affective computing community. The variability in group size makes difficulty for group-level emotion recognition to straightforwardly measure the feature distance of two group-level images. To alleviate this problem, this paper aims to design a new method to effectively analyze the group behavior from a group-level image. Motivated by time-series kernel approaches explored in dynamic facial expression classification, this paper mainly concentrates on global alignment kernel and design support vector machine with the combined global alignment kernels (SVM-CGAK) to better recognize group-level emotion. Intensive experiments are conducted on three challenging group-level emotion databases. The experimental results demonstrate that the proposed approach achieves promising performance for group-level emotion recognition compared with the recent state-of-the-art methods.",
keywords = "Convolution neural network, Facial expression analysis, Global alignment kernels, Group-level emotion recognition, Multiple kernel learning",
author = "Xiaohua Huang and Abhinav Dhall and Roland Goecke and Pietikainen, {Matti K.} and Guoying Zhao",
year = "2019",
month = "11",
day = "14",
doi = "10.1109/TAFFC.2019.2953664",
language = "English",
journal = "IEEE Transactions on Affective Computing",
issn = "1949-3045",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

Analyzing group-level emotion with global alignment kernel based approach. / Huang, Xiaohua; Dhall, Abhinav; Goecke, Roland; Pietikainen, Matti K.; Zhao, Guoying.

In: IEEE Transactions on Affective Computing, 14.11.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analyzing group-level emotion with global alignment kernel based approach

AU - Huang, Xiaohua

AU - Dhall, Abhinav

AU - Goecke, Roland

AU - Pietikainen, Matti K.

AU - Zhao, Guoying

PY - 2019/11/14

Y1 - 2019/11/14

N2 - From the perspective of social science, understanding group emotion has become increasingly important for teams to considerably accomplish organizational work. Currently, automatically analyzing the perceived affect of a group of people has been received increasingly interest in affective computing community. The variability in group size makes difficulty for group-level emotion recognition to straightforwardly measure the feature distance of two group-level images. To alleviate this problem, this paper aims to design a new method to effectively analyze the group behavior from a group-level image. Motivated by time-series kernel approaches explored in dynamic facial expression classification, this paper mainly concentrates on global alignment kernel and design support vector machine with the combined global alignment kernels (SVM-CGAK) to better recognize group-level emotion. Intensive experiments are conducted on three challenging group-level emotion databases. The experimental results demonstrate that the proposed approach achieves promising performance for group-level emotion recognition compared with the recent state-of-the-art methods.

AB - From the perspective of social science, understanding group emotion has become increasingly important for teams to considerably accomplish organizational work. Currently, automatically analyzing the perceived affect of a group of people has been received increasingly interest in affective computing community. The variability in group size makes difficulty for group-level emotion recognition to straightforwardly measure the feature distance of two group-level images. To alleviate this problem, this paper aims to design a new method to effectively analyze the group behavior from a group-level image. Motivated by time-series kernel approaches explored in dynamic facial expression classification, this paper mainly concentrates on global alignment kernel and design support vector machine with the combined global alignment kernels (SVM-CGAK) to better recognize group-level emotion. Intensive experiments are conducted on three challenging group-level emotion databases. The experimental results demonstrate that the proposed approach achieves promising performance for group-level emotion recognition compared with the recent state-of-the-art methods.

KW - Convolution neural network

KW - Facial expression analysis

KW - Global alignment kernels

KW - Group-level emotion recognition

KW - Multiple kernel learning

UR - http://www.scopus.com/inward/record.url?scp=85075397895&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/document/8901205

UR - http://www.mendeley.com/research/analyzing-grouplevel-emotion-global-alignment-kernel-based-approach

U2 - 10.1109/TAFFC.2019.2953664

DO - 10.1109/TAFFC.2019.2953664

M3 - Article

JO - IEEE Transactions on Affective Computing

JF - IEEE Transactions on Affective Computing

SN - 1949-3045

ER -