Improved Xception with Local Dense Connections and Transition Layer for Facial Expression Recognition
Traditional deep convolutional neural networks are used for facial expression recognition, which makes the number of neurons and parameters huge, wastes computing resources, and even causes problems such as overfitting and network degradation. Meanwhile, single-scale expression features cannot descr...
| Published in: | Proceedings of 2024 3rd International Conference on Artificial Intelligence and Intelligent Information Processing, AIIIP 2024 |
|---|---|
| Main Author: | |
| Format: | Conference paper |
| Language: | English |
| Published: |
Association for Computing Machinery, Inc
2025
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85219174176&doi=10.1145%2f3707292.3707398&partnerID=40&md5=1f7308a3da4526322d8aa6a17186e516 |