Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1815009(2022)
Expression Recognition Based on Attention-Split Convolutional Residual Network
Fig. 1. Convolution. (a) Group convolution; (b) point convolution
Fig. 2. Split convolution
Fig. 3. Coordinate attention
Fig. 4. CASCBlock
Fig. 5. Channel attention resolution convolutional residuals network
Fig. 6. Results of FER2013 experiment. (a) ResNet18; (b) SPResNet18_CA
Fig. 7. Results of RAF-DB experiment. (a) ResNet18; (b) SPResNet18_CA
Fig. 8. Accuracy curve comparison chart. (a) FER2013; (b) RAF-DB
|
|
|
|
Get Citation
Copy Citation Text
Jiamin Chen, Yang Xu. Expression Recognition Based on Attention-Split Convolutional Residual Network[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815009
Category: Machine Vision
Received: Jun. 11, 2021
Accepted: Aug. 10, 2021
Published Online: Aug. 30, 2022
The Author Email: Xu Yang (xuy@gzu.edu.cn)