Group expression intensity estimation in videos via Gaussian Processes

Abhinav Dhall, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

15 Citations (Scopus)
1 Downloads (Pure)

Abstract

Facial expression analysis has been a very active field of research in recent years. This paper proposes a method for finding the apex of an expression, e.g. happiness, in a video containing a group of people based on expression intensity estimation. The proposed method is directly applied to video summarisation based on group happiness and timestamps; further, a novel Gaussian Process Regression based expression intensity estimation method is described. To demonstrate its performance, experiments on smile intensity estimation are performed and compared to other regression based techniques. The smile intensity estimator is extended to group happiness intensity estimation. The proposed intensity estimator can be extended easily for other expressions. The experiments are performed on an 'in the wild' dataset. Quantitative results are presented for comparison of our happiness-intensity detector. A user study was also conducted to verify the results of the proposed method.
Original languageEnglish
Title of host publicationProceedings International Conference on Pattern Recognition (ICPR 2012)
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages3525-3528
Number of pages4
ISBN (Electronic)9784990644109
ISBN (Print)9784990644109
Publication statusPublished - 2012
Event21st International Conference on Pattern Recognition (ICPR 2012) - Tsukuba, Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Conference

Conference21st International Conference on Pattern Recognition (ICPR 2012)
Abbreviated titleICPR 2012
CountryJapan
CityTsukuba
Period11/11/1215/11/12

Fingerprint

Experiments
Detectors

Cite this

Dhall, A., & Goecke, R. (2012). Group expression intensity estimation in videos via Gaussian Processes. In Proceedings International Conference on Pattern Recognition (ICPR 2012) (pp. 3525-3528). United States: IEEE, Institute of Electrical and Electronics Engineers.
Dhall, Abhinav ; Goecke, Roland. / Group expression intensity estimation in videos via Gaussian Processes. Proceedings International Conference on Pattern Recognition (ICPR 2012). United States : IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 3525-3528
@inproceedings{9ff44a5129354d80abb88c572ef6170a,
title = "Group expression intensity estimation in videos via Gaussian Processes",
abstract = "Facial expression analysis has been a very active field of research in recent years. This paper proposes a method for finding the apex of an expression, e.g. happiness, in a video containing a group of people based on expression intensity estimation. The proposed method is directly applied to video summarisation based on group happiness and timestamps; further, a novel Gaussian Process Regression based expression intensity estimation method is described. To demonstrate its performance, experiments on smile intensity estimation are performed and compared to other regression based techniques. The smile intensity estimator is extended to group happiness intensity estimation. The proposed intensity estimator can be extended easily for other expressions. The experiments are performed on an 'in the wild' dataset. Quantitative results are presented for comparison of our happiness-intensity detector. A user study was also conducted to verify the results of the proposed method.",
keywords = "Facial expression analysis, face analysis, expression intensity, Gaussian Processes, group mood",
author = "Abhinav Dhall and Roland Goecke",
year = "2012",
language = "English",
isbn = "9784990644109",
pages = "3525--3528",
booktitle = "Proceedings International Conference on Pattern Recognition (ICPR 2012)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Dhall, A & Goecke, R 2012, Group expression intensity estimation in videos via Gaussian Processes. in Proceedings International Conference on Pattern Recognition (ICPR 2012). IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 3525-3528, 21st International Conference on Pattern Recognition (ICPR 2012), Tsukuba, Japan, 11/11/12.

Group expression intensity estimation in videos via Gaussian Processes. / Dhall, Abhinav; Goecke, Roland.

Proceedings International Conference on Pattern Recognition (ICPR 2012). United States : IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 3525-3528.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Group expression intensity estimation in videos via Gaussian Processes

AU - Dhall, Abhinav

AU - Goecke, Roland

PY - 2012

Y1 - 2012

N2 - Facial expression analysis has been a very active field of research in recent years. This paper proposes a method for finding the apex of an expression, e.g. happiness, in a video containing a group of people based on expression intensity estimation. The proposed method is directly applied to video summarisation based on group happiness and timestamps; further, a novel Gaussian Process Regression based expression intensity estimation method is described. To demonstrate its performance, experiments on smile intensity estimation are performed and compared to other regression based techniques. The smile intensity estimator is extended to group happiness intensity estimation. The proposed intensity estimator can be extended easily for other expressions. The experiments are performed on an 'in the wild' dataset. Quantitative results are presented for comparison of our happiness-intensity detector. A user study was also conducted to verify the results of the proposed method.

AB - Facial expression analysis has been a very active field of research in recent years. This paper proposes a method for finding the apex of an expression, e.g. happiness, in a video containing a group of people based on expression intensity estimation. The proposed method is directly applied to video summarisation based on group happiness and timestamps; further, a novel Gaussian Process Regression based expression intensity estimation method is described. To demonstrate its performance, experiments on smile intensity estimation are performed and compared to other regression based techniques. The smile intensity estimator is extended to group happiness intensity estimation. The proposed intensity estimator can be extended easily for other expressions. The experiments are performed on an 'in the wild' dataset. Quantitative results are presented for comparison of our happiness-intensity detector. A user study was also conducted to verify the results of the proposed method.

KW - Facial expression analysis

KW - face analysis

KW - expression intensity

KW - Gaussian Processes

KW - group mood

M3 - Conference contribution

SN - 9784990644109

SP - 3525

EP - 3528

BT - Proceedings International Conference on Pattern Recognition (ICPR 2012)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

ER -

Dhall A, Goecke R. Group expression intensity estimation in videos via Gaussian Processes. In Proceedings International Conference on Pattern Recognition (ICPR 2012). United States: IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 3525-3528