E2‐capsule neural networks for facial expression recognition using AU‐aware attention
Capsule neural network is a new and popular technique in deep learning. However, the traditional capsule neural network does not extract features sufficiently before the dynamic routing between capsules. In this study, one double enhanced capsule neural network (E2‐Capsnet) that uses AU‐aware attent...
Main Authors: | Shan Cao, Yuqian Yao, Gaoyun An |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2020-09-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-ipr.2020.0063 |
Similar Items
-
DE-CapsNet: A Diverse Enhanced Capsule Network with Disperse Dynamic Routing
by: Bohan Jia, et al.
Published: (2020-01-01) -
Deep Neural Networks Using Capsule Networks and Skeleton-Based Attentions for Action Recognition
by: Manh-Hung Ha, et al.
Published: (2021-01-01) -
Capsule Network Improved Multi-Head Attention for Word Sense Disambiguation
by: Jinfeng Cheng, et al.
Published: (2021-03-01) -
From Auto-encoders to Capsule Networks: A Survey
by: El Alaoui-Elfels Omaima, et al.
Published: (2021-01-01) -
From Auto-encoders to Capsule Networks: A Survey
by: El Alaoui-Elfels Omaima, et al.
Published: (2021-01-01)