A Single Hierarchical Network for Face, Action Unit and Emotion Detection

Shreyank Jyoti; Garima Sharma; Abhinav Dhall

doi:10.1109/DICTA.2018.8615852

A Single Hierarchical Network for Face, Action Unit and Emotion Detection

Shreyank Jyoti, Garima Sharma, Abhinav Dhall

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

The deep neural network shows a consequential performance for a set of specific tasks. A system designed for some correlated task altogether can be feasible for 'in the wild' applications. This paper proposes a method for the face localization, Action Unit (AU) and emotion detection. The three different tasks are performed by a simultaneous hierarchical network which exploits the way of learning of neural networks. Such network can represent more relevant features than the individual network. Due to more complex structures and very deep networks, the deployment of neural networks for real life applications is a challenging task. The paper focuses to find an efficient trade-off between the performance and the complexity of the given tasks. This is done by exploring the advantages of optimization of the network for the given tasks by using separable convolutions, binarization and quantization. Four different databases (AffectNet, EmotioNet, RAF-DB and WiderFace) are used to evaluate the performance of our proposed approach by having a separate task specific database.

Original language	English
Title of host publication	2018 International Conference on Digital Image Computing
Subtitle of host publication	Techniques and Applications, DICTA 2018
Editors	Mark Pickering, Lihong Zheng, Shaodi You, Ashfaqur Rahman, Manzur Murshed, Md Asikuzzaman, Ambarish Natu, Antonio Robles-Kelly, Manoranjan Paul
Publisher	Institute of Electrical and Electronics Engineers
Pages	637-644
Number of pages	8
ISBN (Electronic)	9781538666029
DOIs	https://doi.org/10.1109/DICTA.2018.8615852
Publication status	Published - 16 Jan 2019
Externally published	Yes
Event	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 - Canberra, Australia Duration: 10 Dec 2018 → 13 Dec 2018

Publication series

Name	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018

Conference

Conference	2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018
Country/Territory	Australia
City	Canberra
Period	10/12/18 → 13/12/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

AU detection
Emotion detection
Face localization
Hierarchical network

Access to Document

10.1109/DICTA.2018.8615852Licence: In Copyright

Cite this

Jyoti, S., Sharma, G., & Dhall, A. (2019). A Single Hierarchical Network for Face, Action Unit and Emotion Detection. In M. Pickering, L. Zheng, S. You, A. Rahman, M. Murshed, M. Asikuzzaman, A. Natu, A. Robles-Kelly, & M. Paul (Eds.), 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 (pp. 637-644). Article 8615852 (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2018.8615852

Jyoti, Shreyank ; Sharma, Garima ; Dhall, Abhinav. / A Single Hierarchical Network for Face, Action Unit and Emotion Detection. 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. editor / Mark Pickering ; Lihong Zheng ; Shaodi You ; Ashfaqur Rahman ; Manzur Murshed ; Md Asikuzzaman ; Ambarish Natu ; Antonio Robles-Kelly ; Manoranjan Paul. Institute of Electrical and Electronics Engineers, 2019. pp. 637-644 (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018).

@inproceedings{4b58bb86e09a4527aaaaa756f3689bf7,

title = "A Single Hierarchical Network for Face, Action Unit and Emotion Detection",

abstract = "The deep neural network shows a consequential performance for a set of specific tasks. A system designed for some correlated task altogether can be feasible for 'in the wild' applications. This paper proposes a method for the face localization, Action Unit (AU) and emotion detection. The three different tasks are performed by a simultaneous hierarchical network which exploits the way of learning of neural networks. Such network can represent more relevant features than the individual network. Due to more complex structures and very deep networks, the deployment of neural networks for real life applications is a challenging task. The paper focuses to find an efficient trade-off between the performance and the complexity of the given tasks. This is done by exploring the advantages of optimization of the network for the given tasks by using separable convolutions, binarization and quantization. Four different databases (AffectNet, EmotioNet, RAF-DB and WiderFace) are used to evaluate the performance of our proposed approach by having a separate task specific database.",

keywords = "AU detection, Emotion detection, Face localization, Hierarchical network",

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

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018 ; Conference date: 10-12-2018 Through 13-12-2018",

year = "2019",

month = jan,

day = "16",

doi = "10.1109/DICTA.2018.8615852",

language = "English",

series = "2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "637--644",

editor = "Mark Pickering and Lihong Zheng and Shaodi You and Ashfaqur Rahman and Manzur Murshed and Md Asikuzzaman and Ambarish Natu and Antonio Robles-Kelly and Manoranjan Paul",

booktitle = "2018 International Conference on Digital Image Computing",

address = "United States",

}

Jyoti, S, Sharma, G & Dhall, A 2019, A Single Hierarchical Network for Face, Action Unit and Emotion Detection. in M Pickering, L Zheng, S You, A Rahman, M Murshed, M Asikuzzaman, A Natu, A Robles-Kelly & M Paul (eds), 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018., 8615852, 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018, Institute of Electrical and Electronics Engineers, pp. 637-644, 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018, Canberra, Australia, 10/12/18. https://doi.org/10.1109/DICTA.2018.8615852

A Single Hierarchical Network for Face, Action Unit and Emotion Detection. / Jyoti, Shreyank; Sharma, Garima; Dhall, Abhinav.
2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. ed. / Mark Pickering; Lihong Zheng; Shaodi You; Ashfaqur Rahman; Manzur Murshed; Md Asikuzzaman; Ambarish Natu; Antonio Robles-Kelly; Manoranjan Paul. Institute of Electrical and Electronics Engineers, 2019. p. 637-644 8615852 (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Single Hierarchical Network for Face, Action Unit and Emotion Detection

AU - Jyoti, Shreyank

AU - Sharma, Garima

AU - Dhall, Abhinav

PY - 2019/1/16

Y1 - 2019/1/16

N2 - The deep neural network shows a consequential performance for a set of specific tasks. A system designed for some correlated task altogether can be feasible for 'in the wild' applications. This paper proposes a method for the face localization, Action Unit (AU) and emotion detection. The three different tasks are performed by a simultaneous hierarchical network which exploits the way of learning of neural networks. Such network can represent more relevant features than the individual network. Due to more complex structures and very deep networks, the deployment of neural networks for real life applications is a challenging task. The paper focuses to find an efficient trade-off between the performance and the complexity of the given tasks. This is done by exploring the advantages of optimization of the network for the given tasks by using separable convolutions, binarization and quantization. Four different databases (AffectNet, EmotioNet, RAF-DB and WiderFace) are used to evaluate the performance of our proposed approach by having a separate task specific database.

AB - The deep neural network shows a consequential performance for a set of specific tasks. A system designed for some correlated task altogether can be feasible for 'in the wild' applications. This paper proposes a method for the face localization, Action Unit (AU) and emotion detection. The three different tasks are performed by a simultaneous hierarchical network which exploits the way of learning of neural networks. Such network can represent more relevant features than the individual network. Due to more complex structures and very deep networks, the deployment of neural networks for real life applications is a challenging task. The paper focuses to find an efficient trade-off between the performance and the complexity of the given tasks. This is done by exploring the advantages of optimization of the network for the given tasks by using separable convolutions, binarization and quantization. Four different databases (AffectNet, EmotioNet, RAF-DB and WiderFace) are used to evaluate the performance of our proposed approach by having a separate task specific database.

KW - AU detection

KW - Emotion detection

KW - Face localization

KW - Hierarchical network

UR - http://www.scopus.com/inward/record.url?scp=85062217608&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/xpl/conhome/8615628/proceeding

U2 - 10.1109/DICTA.2018.8615852

DO - 10.1109/DICTA.2018.8615852

M3 - Conference contribution

AN - SCOPUS:85062217608

T3 - 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018

SP - 637

EP - 644

BT - 2018 International Conference on Digital Image Computing

A2 - Pickering, Mark

A2 - Zheng, Lihong

A2 - You, Shaodi

A2 - Rahman, Ashfaqur

A2 - Murshed, Manzur

A2 - Asikuzzaman, Md

A2 - Natu, Ambarish

A2 - Robles-Kelly, Antonio

A2 - Paul, Manoranjan

PB - Institute of Electrical and Electronics Engineers

T2 - 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018

Y2 - 10 December 2018 through 13 December 2018

ER -

Jyoti S, Sharma G, Dhall A. A Single Hierarchical Network for Face, Action Unit and Emotion Detection. In Pickering M, Zheng L, You S, Rahman A, Murshed M, Asikuzzaman M, Natu A, Robles-Kelly A, Paul M, editors, 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. Institute of Electrical and Electronics Engineers. 2019. p. 637-644. 8615852. (2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018). doi: 10.1109/DICTA.2018.8615852

A Single Hierarchical Network for Face, Action Unit and Emotion Detection

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this