Marsrocky/Emotiw-Engagement-Prediction

Champion of engagement intensity prediction task in Emotion in the wild Challenge 2018.

Engagement level prediction

It implements the work in the EmotiW18 challenge. In the engagement intensity prediction task, we win the 1st place and the details are refered in our paper "Deep Recurrent Multi-instance Learning with Spatio-temporal Features for Engagement Intensity Prediction. International Conference on Multimodal Interaction (ICMI’18), ACM." (link)

Requirement

• pytorch 0.4.1
• OpenPose
• OpenFace
• LBPTOP

Reference

Please cite the paper if you think it is helpful.

@inproceedings{yang2018deep,
  title={Deep recurrent multi-instance learning with spatio-temporal features for engagement intensity prediction},
  author={Yang, Jianfei and Wang, Kai and Peng, Xiaojiang and Qiao, Yu},
  booktitle={Proceedings of the 20th ACM international conference on multimodal interaction},
  pages={594--598},
  year={2018}
}