Miskow, A and Altahhan, A orcid.org/0000-0003-1133-7744 (2023) Emotion Recognition with Facial Attention and Objective Activation Functions. In: Tanveer, M, Agarwal, S, Ozawa, S, Ekbal, A and Jatowt, A, (eds.) Neural Information Processing. 29th International Conference, ICONIP 2022, 22-26 Nov 2022, New Delhi, India. Communications in Computer and Information Science, 1792 . Springer Nature , pp. 504-515. ISBN 978-981-99-1641-2
Abstract
In this paper, we study the effect of introducing channel and spatial attention mechanisms, namely SEN-Net, ECA-Net, and CBAM, to existing CNN vision-based models such as VGGNet, ResNet, and ResNetV2 to perform the Facial Emotion Recognition task. We show that not only attention can significantly improve the performance of these models but also that combining them with a different activation function can further help increase the performance of these models.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2023 The Author(s). This is an author produced version of a conference paper published in Neural Information Processing. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Facial Emotion Recognition; Attention; Activation Functions; VGGNet; Resnet; ResNetV2; SEN-net; ECA-Net; CBAM |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 15 Dec 2022 11:40 |
Last Modified: | 14 Apr 2024 00:13 |
Status: | Published |
Publisher: | Springer Nature |
Series Name: | Communications in Computer and Information Science |
Identification Number: | 10.1007/978-981-99-1642-9_43 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:193999 |