Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods

Damien Dupre, Nicole Andelic, Gawain Morrison, Gary McKeown

Research output: Chapter in Book/Report/Conference proceedingConference contribution

61 Downloads (Pure)

Abstract

The analysis of facial expressions is currently a favored method of inferring experienced emotion, and consequently significant efforts are currently be-ing made to develop improved facial expression recognition techniques. Among these new techniques, those which allow the automatic recognition of facial expression appear to be most promising. This paper presents a new method of facial expression analysis with a focus on the continuous evolu-tion of emotions using Generalized Additive Mixed Models and Significant Zero Crossing of the Derivative (SiZer). The time-series analysis of the emo-tions experienced by participants watching a series of three different online videos suggests that analysis of facial expressions at the overall level may lead to misinterpretation of the emotional experience whereas non-linear analysis allows the significant expressive sequences to be identified.
Original languageEnglish
Title of host publication20th International Conference on Human-Computer Interaction
Number of pages13
Publication statusPublished - 20 Jul 2018
Event20th International Conference on Human-Computer Interaction - Las Vegas, United States
Duration: 15 Jul 201820 Jul 2018

Conference

Conference20th International Conference on Human-Computer Interaction
Abbreviated titleHCII 2018
CountryUnited States
CityLas Vegas
Period15/07/201820/07/2018

Fingerprint

Time series analysis
Nonlinear analysis
Derivatives

Cite this

Dupre, D., Andelic, N., Morrison, G., & McKeown, G. (2018). Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods. In 20th International Conference on Human-Computer Interaction
Dupre, Damien ; Andelic, Nicole ; Morrison, Gawain ; McKeown, Gary. / Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods. 20th International Conference on Human-Computer Interaction. 2018.
@inproceedings{b0bb7a822a40480f830763226da7cdcd,
title = "Assessment of automatic facial expressions recognition {"}in the wild{"}: a time-series analysis using GAMM and SiZer methods",
abstract = "The analysis of facial expressions is currently a favored method of inferring experienced emotion, and consequently significant efforts are currently be-ing made to develop improved facial expression recognition techniques. Among these new techniques, those which allow the automatic recognition of facial expression appear to be most promising. This paper presents a new method of facial expression analysis with a focus on the continuous evolu-tion of emotions using Generalized Additive Mixed Models and Significant Zero Crossing of the Derivative (SiZer). The time-series analysis of the emo-tions experienced by participants watching a series of three different online videos suggests that analysis of facial expressions at the overall level may lead to misinterpretation of the emotional experience whereas non-linear analysis allows the significant expressive sequences to be identified.",
author = "Damien Dupre and Nicole Andelic and Gawain Morrison and Gary McKeown",
year = "2018",
month = "7",
day = "20",
language = "English",
booktitle = "20th International Conference on Human-Computer Interaction",

}

Dupre, D, Andelic, N, Morrison, G & McKeown, G 2018, Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods. in 20th International Conference on Human-Computer Interaction. 20th International Conference on Human-Computer Interaction, Las Vegas, United States, 15/07/2018.

Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods. / Dupre, Damien; Andelic, Nicole; Morrison, Gawain; McKeown, Gary.

20th International Conference on Human-Computer Interaction. 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods

AU - Dupre, Damien

AU - Andelic, Nicole

AU - Morrison, Gawain

AU - McKeown, Gary

PY - 2018/7/20

Y1 - 2018/7/20

N2 - The analysis of facial expressions is currently a favored method of inferring experienced emotion, and consequently significant efforts are currently be-ing made to develop improved facial expression recognition techniques. Among these new techniques, those which allow the automatic recognition of facial expression appear to be most promising. This paper presents a new method of facial expression analysis with a focus on the continuous evolu-tion of emotions using Generalized Additive Mixed Models and Significant Zero Crossing of the Derivative (SiZer). The time-series analysis of the emo-tions experienced by participants watching a series of three different online videos suggests that analysis of facial expressions at the overall level may lead to misinterpretation of the emotional experience whereas non-linear analysis allows the significant expressive sequences to be identified.

AB - The analysis of facial expressions is currently a favored method of inferring experienced emotion, and consequently significant efforts are currently be-ing made to develop improved facial expression recognition techniques. Among these new techniques, those which allow the automatic recognition of facial expression appear to be most promising. This paper presents a new method of facial expression analysis with a focus on the continuous evolu-tion of emotions using Generalized Additive Mixed Models and Significant Zero Crossing of the Derivative (SiZer). The time-series analysis of the emo-tions experienced by participants watching a series of three different online videos suggests that analysis of facial expressions at the overall level may lead to misinterpretation of the emotional experience whereas non-linear analysis allows the significant expressive sequences to be identified.

M3 - Conference contribution

BT - 20th International Conference on Human-Computer Interaction

ER -

Dupre D, Andelic N, Morrison G, McKeown G. Assessment of automatic facial expressions recognition "in the wild": a time-series analysis using GAMM and SiZer methods. In 20th International Conference on Human-Computer Interaction. 2018