agnusa / dssn-mer

Dual Stream Shallow AlexNets

Note:

Please only email to me for inquiries, do not email to co-authors as they are faculty members or professors who have tonnes of work to do, emailing them may create burden for them. let's care for the well-being of our professors :)

Environment

Python 3.6, Keras 2, theano bleeding edge,

Dual-Stream-Shallow-Networks-for-Facial-Micro-Expression-Recognition

Dual Stream Shallow AlexNets

Pre-requisite tools

https://github.com/heuritech/convnets-keras (for pre-trained alexnet)

SSSN & DSSN Weights for Reported Results in Table 1.

https://drive.google.com/drive/folders/11e5Ezw-hZrNkjryDsfVa2TIg5lYGiRsh?usp=sharing

Image samples used:

https://drive.google.com/file/d/1C9ZrHUDvCibuW2PR_o9OUKQmMZ--eGaW/view?usp=sharing

Find you find the work useful, please cite as below:

@inproceedings{khor2019dual,
title={Dual-stream Shallow Networks for Facial Micro-expression Recognition},
author={Khor, Huai-Qian and See, John and Liong, Sze-Teng and Phan, Raphael CW and Lin, Weiyao},
booktitle={2019 IEEE International Conference on Image Processing (ICIP)},
pages={36--40},
year={2019},
organization={IEEE}
}