Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Deep Discovery of Facial Motions using a Shallow Embedding Layer

Abstract: 

Unique encoding of the dynamics of facial actions has potential to provide a spontaneous facial expression recognition system. The most promising existing approaches rely on deep learning of facial actions. However, current approaches are often computationally intensive and require a great deal of memory/processing time, and typically the temporal aspect of facial actions are often ignored, despite the potential wealth of information available from the spatial dynamic movements and their temporal evolution over time from neutral state to apex state. To tackle aforementioned challenges, we propose a deep learning framework by using the 3D convolutional filters to extract spatio-temporal features, followed by the LSTM network which is able to integrate the dynamic evolution of short-duration of spatio-temporal features as an emotion progresses from the neutral state to the apex state.
In order to reduce the redundancy of parameters and accelerate the learning of the recurrent neural network, we propose a shallow embedding layer to reduce the number of parameters in the LSTM by up to 98% without sacrificing recognition accuracy. As the fully connected layer approximately contains 95% of the parameters in the network, we decrease the number of parameters in this layer before passing features to the LSTM network, which significantly improves training speed and enables the possibility of deploying a state of the art deep network on real-time applications. We evaluate our proposed
framework on the DISFA and UNBC-McMaster Shoulder pain datasets.

ICIP.pdf

PDF icon ICIP.pdf (83 downloads)
up
0 users have voted:

Paper Details

Authors:
Afsaneh Ghasemi, Mahsa Baktashmotlagh, Simon Denman, Sridha Sridharan, Dung Nguyen Tien, Clinton Fookes
Submitted On:
17 September 2017 - 4:03am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Afsaneh Ghasemi
Paper Code:
2171
Document Year:
2017
Cite

Document Files

ICIP.pdf

(83 downloads)

Subscribe

[1] Afsaneh Ghasemi, Mahsa Baktashmotlagh, Simon Denman, Sridha Sridharan, Dung Nguyen Tien, Clinton Fookes, "Deep Discovery of Facial Motions using a Shallow Embedding Layer", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2211. Accessed: Apr. 19, 2018.
@article{2211-17,
url = {http://sigport.org/2211},
author = {Afsaneh Ghasemi; Mahsa Baktashmotlagh; Simon Denman; Sridha Sridharan; Dung Nguyen Tien; Clinton Fookes },
publisher = {IEEE SigPort},
title = {Deep Discovery of Facial Motions using a Shallow Embedding Layer},
year = {2017} }
TY - EJOUR
T1 - Deep Discovery of Facial Motions using a Shallow Embedding Layer
AU - Afsaneh Ghasemi; Mahsa Baktashmotlagh; Simon Denman; Sridha Sridharan; Dung Nguyen Tien; Clinton Fookes
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2211
ER -
Afsaneh Ghasemi, Mahsa Baktashmotlagh, Simon Denman, Sridha Sridharan, Dung Nguyen Tien, Clinton Fookes. (2017). Deep Discovery of Facial Motions using a Shallow Embedding Layer. IEEE SigPort. http://sigport.org/2211
Afsaneh Ghasemi, Mahsa Baktashmotlagh, Simon Denman, Sridha Sridharan, Dung Nguyen Tien, Clinton Fookes, 2017. Deep Discovery of Facial Motions using a Shallow Embedding Layer. Available at: http://sigport.org/2211.
Afsaneh Ghasemi, Mahsa Baktashmotlagh, Simon Denman, Sridha Sridharan, Dung Nguyen Tien, Clinton Fookes. (2017). "Deep Discovery of Facial Motions using a Shallow Embedding Layer." Web.
1. Afsaneh Ghasemi, Mahsa Baktashmotlagh, Simon Denman, Sridha Sridharan, Dung Nguyen Tien, Clinton Fookes. Deep Discovery of Facial Motions using a Shallow Embedding Layer [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2211