FERA 2015 - second Facial Expression Recognition and Analysis challenge

Michel F. Valstar; Timur Almaev; Jeffrey M. Girard; Gary McKeown; Marc Mehu; Lijun Yin; Maja Pantic; Jeffrey F. Cohn

doi:10.1109/FG.2015.7284874

FERA 2015 - second Facial Expression Recognition and Analysis challenge

Michel F. Valstar, Timur Almaev, Jeffrey M. Girard, Gary McKeown, Marc Mehu, Lijun Yin, Maja Pantic, Jeffrey F. Cohn

School of Psychology

Research output: Chapter in Book/Report/Conference proceeding › Chapter

181 Citations (Scopus)

Abstract

Despite efforts towards evaluation standards in facial expression analysis (e.g. FERA 2011), there is a need for up-to-date standardised evaluation procedures, focusing in particular on current challenges in the field. One of the challenges that is actively being addressed is the automatic estimation of expression intensities. To continue to provide a standardisation platform and to help the field progress beyond its current limitations, the FG 2015 Facial Expression Recognition and Analysis challenge (FERA 2015) will challenge participants to estimate FACS Action Unit (AU) intensity as well as AU occurrence on a common benchmark dataset with reliable manual annotations. Evaluation will be done using a clear and well-defined protocol. In this paper we present the second such challenge in automatic recognition of facial expressions, to be held in conjunction with the 11 IEEE conference on Face and Gesture Recognition, May 2015, in Ljubljana, Slovenia. Three sub-challenges are defined: the detection of AU occurrence, the estimation of AU intensity for pre-segmented data, and fully automatic AU intensity estimation. In this work we outline the evaluation protocol, the data used, and the results of a baseline method for the three sub-challenges.

Original language	English
Title of host publication	2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-8
Number of pages	8
ISBN (Print)	978-1-4799-6026-2
DOIs	https://doi.org/10.1109/FG.2015.7284874
Publication status	Published - May 2015

Publication series

Name	2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
Volume	06

Keywords

AU intensity
AU occurrence
Databases
Estimation
FACS action unit
FERA 2015
Face recognition
Feature extraction
Gold
Reliability
Training
emotion recognition
expression intensities estimation
face recognition
facial expression analysis
facial expression recognition and analysis challen
standardisation platform

Access to Document

10.1109/FG.2015.7284874

Cite this

Valstar, M. F., Almaev, T., Girard, J. M., McKeown, G., Mehu, M., Yin, L., Pantic, M., & Cohn, J. F. (2015). FERA 2015 - second Facial Expression Recognition and Analysis challenge. In 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) (pp. 1-8). (2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG); Vol. 06). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FG.2015.7284874

Valstar, Michel F. ; Almaev, Timur ; Girard, Jeffrey M. et al. / FERA 2015 - second Facial Expression Recognition and Analysis challenge. 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1-8 (2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)).

@inbook{d0e216e64bd1434d8ab8eaf6c605dc3b,

title = "FERA 2015 - second Facial Expression Recognition and Analysis challenge",

abstract = "Despite efforts towards evaluation standards in facial expression analysis (e.g. FERA 2011), there is a need for up-to-date standardised evaluation procedures, focusing in particular on current challenges in the field. One of the challenges that is actively being addressed is the automatic estimation of expression intensities. To continue to provide a standardisation platform and to help the field progress beyond its current limitations, the FG 2015 Facial Expression Recognition and Analysis challenge (FERA 2015) will challenge participants to estimate FACS Action Unit (AU) intensity as well as AU occurrence on a common benchmark dataset with reliable manual annotations. Evaluation will be done using a clear and well-defined protocol. In this paper we present the second such challenge in automatic recognition of facial expressions, to be held in conjunction with the 11 IEEE conference on Face and Gesture Recognition, May 2015, in Ljubljana, Slovenia. Three sub-challenges are defined: the detection of AU occurrence, the estimation of AU intensity for pre-segmented data, and fully automatic AU intensity estimation. In this work we outline the evaluation protocol, the data used, and the results of a baseline method for the three sub-challenges.",

keywords = "AU intensity, AU occurrence, Databases, Estimation, FACS action unit, FERA 2015, Face recognition, Feature extraction, Gold, Reliability, Training, emotion recognition, expression intensities estimation, face recognition, facial expression analysis, facial expression recognition and analysis challen, standardisation platform",

author = "Valstar, {Michel F.} and Timur Almaev and Girard, {Jeffrey M.} and Gary McKeown and Marc Mehu and Lijun Yin and Maja Pantic and Cohn, {Jeffrey F.}",

year = "2015",

month = may,

doi = "10.1109/FG.2015.7284874",

language = "English",

isbn = "978-1-4799-6026-2",

series = "2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--8",

booktitle = "2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)",

address = "United States",

}

Valstar, MF, Almaev, T, Girard, JM, McKeown, G, Mehu, M, Yin, L, Pantic, M & Cohn, JF 2015, FERA 2015 - second Facial Expression Recognition and Analysis challenge. in 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 06, Institute of Electrical and Electronics Engineers Inc., pp. 1-8. https://doi.org/10.1109/FG.2015.7284874

FERA 2015 - second Facial Expression Recognition and Analysis challenge. / Valstar, Michel F.; Almaev, Timur; Girard, Jeffrey M. et al.
2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). Institute of Electrical and Electronics Engineers Inc., 2015. p. 1-8 (2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG); Vol. 06).

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - FERA 2015 - second Facial Expression Recognition and Analysis challenge

AU - Valstar, Michel F.

AU - Almaev, Timur

AU - Girard, Jeffrey M.

AU - McKeown, Gary

AU - Mehu, Marc

AU - Yin, Lijun

AU - Pantic, Maja

AU - Cohn, Jeffrey F.

PY - 2015/5

Y1 - 2015/5

N2 - Despite efforts towards evaluation standards in facial expression analysis (e.g. FERA 2011), there is a need for up-to-date standardised evaluation procedures, focusing in particular on current challenges in the field. One of the challenges that is actively being addressed is the automatic estimation of expression intensities. To continue to provide a standardisation platform and to help the field progress beyond its current limitations, the FG 2015 Facial Expression Recognition and Analysis challenge (FERA 2015) will challenge participants to estimate FACS Action Unit (AU) intensity as well as AU occurrence on a common benchmark dataset with reliable manual annotations. Evaluation will be done using a clear and well-defined protocol. In this paper we present the second such challenge in automatic recognition of facial expressions, to be held in conjunction with the 11 IEEE conference on Face and Gesture Recognition, May 2015, in Ljubljana, Slovenia. Three sub-challenges are defined: the detection of AU occurrence, the estimation of AU intensity for pre-segmented data, and fully automatic AU intensity estimation. In this work we outline the evaluation protocol, the data used, and the results of a baseline method for the three sub-challenges.

AB - Despite efforts towards evaluation standards in facial expression analysis (e.g. FERA 2011), there is a need for up-to-date standardised evaluation procedures, focusing in particular on current challenges in the field. One of the challenges that is actively being addressed is the automatic estimation of expression intensities. To continue to provide a standardisation platform and to help the field progress beyond its current limitations, the FG 2015 Facial Expression Recognition and Analysis challenge (FERA 2015) will challenge participants to estimate FACS Action Unit (AU) intensity as well as AU occurrence on a common benchmark dataset with reliable manual annotations. Evaluation will be done using a clear and well-defined protocol. In this paper we present the second such challenge in automatic recognition of facial expressions, to be held in conjunction with the 11 IEEE conference on Face and Gesture Recognition, May 2015, in Ljubljana, Slovenia. Three sub-challenges are defined: the detection of AU occurrence, the estimation of AU intensity for pre-segmented data, and fully automatic AU intensity estimation. In this work we outline the evaluation protocol, the data used, and the results of a baseline method for the three sub-challenges.

KW - AU intensity

KW - AU occurrence

KW - Databases

KW - Estimation

KW - FACS action unit

KW - FERA 2015

KW - Face recognition

KW - Feature extraction

KW - Gold

KW - Reliability

KW - Training

KW - emotion recognition

KW - expression intensities estimation

KW - face recognition

KW - facial expression analysis

KW - facial expression recognition and analysis challen

KW - standardisation platform

U2 - 10.1109/FG.2015.7284874

DO - 10.1109/FG.2015.7284874

M3 - Chapter

SN - 978-1-4799-6026-2

T3 - 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

SP - 1

EP - 8

BT - 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Valstar MF, Almaev T, Girard JM, McKeown G, Mehu M, Yin L et al. FERA 2015 - second Facial Expression Recognition and Analysis challenge. In 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG). Institute of Electrical and Electronics Engineers Inc. 2015. p. 1-8. (2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)). doi: 10.1109/FG.2015.7284874

FERA 2015 - second Facial Expression Recognition and Analysis challenge

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this