Recognition of Affect in the wild using Deep Neural Networks

Dimitrios, Kollias; Mihalis, Nicolao; Irene, Kotsia; Guoying, Zhao and Stefanos, Zafeiriou. 2017. 'Recognition of Affect in the wild using Deep Neural Networks'. In: CVPR (Computer Vision and Pattern Recognition). Hawaii, United States 21 - 26 July 2017. [Conference or Workshop Item]

Text (Open Access Version provided by the Computer Vision Foundation)
DNN_AffWld_CVPRW17.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (727kB) | Preview

Abstract or Description

In this paper we utilize the first large-scale ”in-the-wild” (Aff-Wild) database, which is annotated in terms of the valence-arousal dimensions, to train and test an end-to-end deep neural architecture for the estimation of continuous emotion dimensions based on visual cues. The proposed architecture is based on jointly training convolutional (CNN) and recurrent neural network (RNN) layers, thus exploiting both the invariant properties of convolutional features, while also modelling temporal dynamics that arise in human behaviour via the recurrent layers. Various pre-trained networks are used as starting structures which are subsequently appropriately fine-tuned to the Aff-Wild database. Obtained results show premise for the utilization of deep architectures for the visual analysis of human behaviour in terms of continuous emotion dimensions and analysis of different types of affect.

Item Type:

Conference or Workshop Item (Talk)

Departments, Centres and Research Units:



20 April 2017Accepted
25 July 2017Published

Event Location:

Hawaii, United States

Date range:

21 - 26 July 2017

Item ID:


Date Deposited:

07 Sep 2017 10:23

Last Modified:

29 Apr 2020 16:32


View statistics for this item...

Edit Record Edit Record (login required)