Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark

Abhinav Dhall, Roland Goecke, Tamas Gedeon, Simon Lucey

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

125 Citations (Scopus)

Abstract

Quality data recorded in varied realistic environments is vital for effective human face related research. Currently available datasets for human facial expression analysis have been generated in highly controlled lab environments. We present a new static facial expression database Static Facial Expressions in the Wild (SFEW) extracted from a temporal facial expressions database Acted Facial Expressions in the Wild (AFEW) [9], which we have extracted from movies. In the past, many robust methods have been reported in the literature. However, these methods have been experimented on different databases or using different protocols within the same databases. The lack of a standard protocol makes it difficult to compare systems and acts as a hindrance in the progress of the field. Therefore, we propose a person independent training and testing protocol for expression recognition as part of the BEFIT workshop. Further, we compare our dataset with the JAFFE and Multi-PIE datasets and provide baseline results.
Original languageEnglish
Title of host publicationProceedings of the 2011 IEEE International Conference on Computer Vision Workshops
EditorsHazam Kemal Ekenel, Gang Hua, Shiguang Shan
Place of PublicationBarcelona, Spain
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2106-2112
Number of pages7
ISBN (Electronic)9781467300636, 9781467300612
ISBN (Print)9781467300629
DOIs
Publication statusPublished - 6 Nov 2011
Event2011 IEEE International Conference on Computer Vision ICCV2011 - Barcelona, Barcelona, Spain
Duration: 6 Nov 201113 Nov 2011

Conference

Conference2011 IEEE International Conference on Computer Vision ICCV2011
CountrySpain
CityBarcelona
Period6/11/1113/11/11

Fingerprint

Testing

Cite this

Dhall, A., Goecke, R., Gedeon, T., & Lucey, S. (2011). Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark. In H. K. Ekenel, G. Hua, & S. Shan (Eds.), Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops (pp. 2106-2112). Barcelona, Spain: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICCVW.2011.6130508
Dhall, Abhinav ; Goecke, Roland ; Gedeon, Tamas ; Lucey, Simon. / Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark. Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops. editor / Hazam Kemal Ekenel ; Gang Hua ; Shiguang Shan. Barcelona, Spain : IEEE, Institute of Electrical and Electronics Engineers, 2011. pp. 2106-2112
@inproceedings{47fa1fd272344d2297d19ffced63f788,
title = "Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark",
abstract = "Quality data recorded in varied realistic environments is vital for effective human face related research. Currently available datasets for human facial expression analysis have been generated in highly controlled lab environments. We present a new static facial expression database Static Facial Expressions in the Wild (SFEW) extracted from a temporal facial expressions database Acted Facial Expressions in the Wild (AFEW) [9], which we have extracted from movies. In the past, many robust methods have been reported in the literature. However, these methods have been experimented on different databases or using different protocols within the same databases. The lack of a standard protocol makes it difficult to compare systems and acts as a hindrance in the progress of the field. Therefore, we propose a person independent training and testing protocol for expression recognition as part of the BEFIT workshop. Further, we compare our dataset with the JAFFE and Multi-PIE datasets and provide baseline results.",
keywords = "Facial expression recognition, Dataset",
author = "Abhinav Dhall and Roland Goecke and Tamas Gedeon and Simon Lucey",
year = "2011",
month = "11",
day = "6",
doi = "10.1109/ICCVW.2011.6130508",
language = "English",
isbn = "9781467300629",
pages = "2106--2112",
editor = "Ekenel, {Hazam Kemal} and Gang Hua and Shiguang Shan",
booktitle = "Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Dhall, A, Goecke, R, Gedeon, T & Lucey, S 2011, Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark. in HK Ekenel, G Hua & S Shan (eds), Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops. IEEE, Institute of Electrical and Electronics Engineers, Barcelona, Spain, pp. 2106-2112, 2011 IEEE International Conference on Computer Vision ICCV2011, Barcelona, Spain, 6/11/11. https://doi.org/10.1109/ICCVW.2011.6130508

Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark. / Dhall, Abhinav; Goecke, Roland; Gedeon, Tamas; Lucey, Simon.

Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops. ed. / Hazam Kemal Ekenel; Gang Hua; Shiguang Shan. Barcelona, Spain : IEEE, Institute of Electrical and Electronics Engineers, 2011. p. 2106-2112.

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

TY - GEN

T1 - Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark

AU - Dhall, Abhinav

AU - Goecke, Roland

AU - Gedeon, Tamas

AU - Lucey, Simon

PY - 2011/11/6

Y1 - 2011/11/6

N2 - Quality data recorded in varied realistic environments is vital for effective human face related research. Currently available datasets for human facial expression analysis have been generated in highly controlled lab environments. We present a new static facial expression database Static Facial Expressions in the Wild (SFEW) extracted from a temporal facial expressions database Acted Facial Expressions in the Wild (AFEW) [9], which we have extracted from movies. In the past, many robust methods have been reported in the literature. However, these methods have been experimented on different databases or using different protocols within the same databases. The lack of a standard protocol makes it difficult to compare systems and acts as a hindrance in the progress of the field. Therefore, we propose a person independent training and testing protocol for expression recognition as part of the BEFIT workshop. Further, we compare our dataset with the JAFFE and Multi-PIE datasets and provide baseline results.

AB - Quality data recorded in varied realistic environments is vital for effective human face related research. Currently available datasets for human facial expression analysis have been generated in highly controlled lab environments. We present a new static facial expression database Static Facial Expressions in the Wild (SFEW) extracted from a temporal facial expressions database Acted Facial Expressions in the Wild (AFEW) [9], which we have extracted from movies. In the past, many robust methods have been reported in the literature. However, these methods have been experimented on different databases or using different protocols within the same databases. The lack of a standard protocol makes it difficult to compare systems and acts as a hindrance in the progress of the field. Therefore, we propose a person independent training and testing protocol for expression recognition as part of the BEFIT workshop. Further, we compare our dataset with the JAFFE and Multi-PIE datasets and provide baseline results.

KW - Facial expression recognition

KW - Dataset

U2 - 10.1109/ICCVW.2011.6130508

DO - 10.1109/ICCVW.2011.6130508

M3 - Conference contribution

SN - 9781467300629

SP - 2106

EP - 2112

BT - Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops

A2 - Ekenel, Hazam Kemal

A2 - Hua, Gang

A2 - Shan, Shiguang

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Barcelona, Spain

ER -

Dhall A, Goecke R, Gedeon T, Lucey S. Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark. In Ekenel HK, Hua G, Shan S, editors, Proceedings of the 2011 IEEE International Conference on Computer Vision Workshops. Barcelona, Spain: IEEE, Institute of Electrical and Electronics Engineers. 2011. p. 2106-2112 https://doi.org/10.1109/ICCVW.2011.6130508