Expression empowered ResiDen network for Facial Action Unit detection

Shreyank Jyoti; Garima Sharma; Abhinav Dhall

doi:10.1109/FG.2019.8756580

Expression empowered ResiDen network for Facial Action Unit detection

Shreyank Jyoti, Garima Sharma, Abhinav Dhall

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

14 Citations (Scopus)

Abstract

The paper explores the topic of Facial Action Unit (FAU) detection in the wild. In particular, we are interested in answering the following questions: (1) How useful are residual connections across dense blocks for face analysis? (2) How useful is the information from a network trained for categorical Facial Expression Recognition (FER) for the task of FAU detection? The proposed network (ResiDen) exploits dense blocks along with residual connections and uses auxiliary information from a FER network. The experiments are performed on the EmotionNet and DISFA datasets. The experiments show the usefulness of facial expression information for AU detection. The proposed network achieves state-of-the-art results on the two datasets. Analysis of the results for cross dataset protocol shows the effectiveness of the network.

Original language	English
Title of host publication	Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019
Editors	Peter Hancock, Richa Singh, Catherine Pelachaud, Vassilis Athitsos
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	262-269
Number of pages	8
ISBN (Electronic)	9781728100890, 9781728100883
ISBN (Print)	9781728100906
DOIs	https://doi.org/10.1109/FG.2019.8756580
Publication status	Published - 2019
Externally published	Yes
Event	IEEE International Conference on Automatic Face and Gesture Recognition 2019 - Lille, France Duration: 14 May 2019 → 18 May 2019 Conference number: 14th https://www.aconf.org/conf_158479.html

Conference

Conference	IEEE International Conference on Automatic Face and Gesture Recognition 2019
Abbreviated title	FG 2019
Country/Territory	France
City	Lille
Period	14/05/19 → 18/05/19
Internet address	https://www.aconf.org/conf_158479.html

Access to Document

10.1109/FG.2019.8756580

Cite this

Jyoti, S., Sharma, G., & Dhall, A. (2019). Expression empowered ResiDen network for Facial Action Unit detection. In P. Hancock, R. Singh, C. Pelachaud, & V. Athitsos (Eds.), Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019 (pp. 262-269). [8756580] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FG.2019.8756580

Jyoti, Shreyank ; Sharma, Garima ; Dhall, Abhinav. / Expression empowered ResiDen network for Facial Action Unit detection. Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019. editor / Peter Hancock ; Richa Singh ; Catherine Pelachaud ; Vassilis Athitsos. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 262-269

@inproceedings{5ec7dbb820e54bb392d0ceda6d1f1e11,

title = "Expression empowered ResiDen network for Facial Action Unit detection",

abstract = "The paper explores the topic of Facial Action Unit (FAU) detection in the wild. In particular, we are interested in answering the following questions: (1) How useful are residual connections across dense blocks for face analysis? (2) How useful is the information from a network trained for categorical Facial Expression Recognition (FER) for the task of FAU detection? The proposed network (ResiDen) exploits dense blocks along with residual connections and uses auxiliary information from a FER network. The experiments are performed on the EmotionNet and DISFA datasets. The experiments show the usefulness of facial expression information for AU detection. The proposed network achieves state-of-the-art results on the two datasets. Analysis of the results for cross dataset protocol shows the effectiveness of the network.",

author = "Shreyank Jyoti and Garima Sharma and Abhinav Dhall",

year = "2019",

doi = "10.1109/FG.2019.8756580",

language = "English",

isbn = "9781728100906",

pages = "262--269",

editor = "Hancock, {Peter } and Singh, {Richa } and Pelachaud, {Catherine } and Athitsos, {Vassilis }",

booktitle = "Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Conference on Automatic Face and Gesture Recognition 2019, FG 2019 ; Conference date: 14-05-2019 Through 18-05-2019",

url = "https://www.aconf.org/conf_158479.html",

}

Jyoti, S, Sharma, G & Dhall, A 2019, Expression empowered ResiDen network for Facial Action Unit detection. in P Hancock, R Singh, C Pelachaud & V Athitsos (eds), Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019., 8756580, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 262-269, IEEE International Conference on Automatic Face and Gesture Recognition 2019, Lille, France, 14/05/19. https://doi.org/10.1109/FG.2019.8756580

Expression empowered ResiDen network for Facial Action Unit detection. / Jyoti, Shreyank; Sharma, Garima; Dhall, Abhinav.

Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019. ed. / Peter Hancock; Richa Singh; Catherine Pelachaud; Vassilis Athitsos. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 262-269 8756580.

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

TY - GEN

T1 - Expression empowered ResiDen network for Facial Action Unit detection

AU - Jyoti, Shreyank

AU - Sharma, Garima

AU - Dhall, Abhinav

N1 - Conference code: 14th

PY - 2019

Y1 - 2019

N2 - The paper explores the topic of Facial Action Unit (FAU) detection in the wild. In particular, we are interested in answering the following questions: (1) How useful are residual connections across dense blocks for face analysis? (2) How useful is the information from a network trained for categorical Facial Expression Recognition (FER) for the task of FAU detection? The proposed network (ResiDen) exploits dense blocks along with residual connections and uses auxiliary information from a FER network. The experiments are performed on the EmotionNet and DISFA datasets. The experiments show the usefulness of facial expression information for AU detection. The proposed network achieves state-of-the-art results on the two datasets. Analysis of the results for cross dataset protocol shows the effectiveness of the network.

AB - The paper explores the topic of Facial Action Unit (FAU) detection in the wild. In particular, we are interested in answering the following questions: (1) How useful are residual connections across dense blocks for face analysis? (2) How useful is the information from a network trained for categorical Facial Expression Recognition (FER) for the task of FAU detection? The proposed network (ResiDen) exploits dense blocks along with residual connections and uses auxiliary information from a FER network. The experiments are performed on the EmotionNet and DISFA datasets. The experiments show the usefulness of facial expression information for AU detection. The proposed network achieves state-of-the-art results on the two datasets. Analysis of the results for cross dataset protocol shows the effectiveness of the network.

UR - http://www.scopus.com/inward/record.url?scp=85070465136&partnerID=8YFLogxK

U2 - 10.1109/FG.2019.8756580

DO - 10.1109/FG.2019.8756580

M3 - Conference Paper

SN - 9781728100906

SP - 262

EP - 269

BT - Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019

A2 - Hancock, Peter

A2 - Singh, Richa

A2 - Pelachaud, Catherine

A2 - Athitsos, Vassilis

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE International Conference on Automatic Face and Gesture Recognition 2019

Y2 - 14 May 2019 through 18 May 2019

ER -

Jyoti S, Sharma G, Dhall A. Expression empowered ResiDen network for Facial Action Unit detection. In Hancock P, Singh R, Pelachaud C, Athitsos V, editors, Proceedings - 14th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2019. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 262-269. 8756580 https://doi.org/10.1109/FG.2019.8756580

Expression empowered ResiDen network for Facial Action Unit detection

Abstract

Conference

Access to Document

Other files and links

Cite this