Research Article
A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
Table 2
Architectures of face identifier. “
” stands for kernel size, “
” means stride, and “
” is padding number.
| | Input | Color-scale image |
| | Convolution | Outputs: 28, : , : 1, : 1 | | MaxPooling | : , : 2 | | Convolution | Outputs: 48, : , : 1, : 1 | | MaxPooling | : , : 2 | | Convolution | Outputs: 64, : , : 1, : 1 | | Convolution | Outputs: 128, : , : 1, : 1 | | Convolution | Outputs: 2, : , : 1, : 1 |
|
|
