Facial Expressions Recognition (Affective Computing)

The objective of this project is to develop and implement state-of-the-art computer vision algorithms for recognition of facial expressions. Our focus is on using deep neural networks on in-the-wild dataset of facial expressions.




Related Publications:

  1. Xiao Zhang, Mohammad H. Mahoor, and S.Mohammad Mavadati, “Facial Expression Recognition Using lp-norm MKL Multiclass-SVM”, Machine Vision and Applications, 26(4), 467-483, 2015.
  2. M.R.Mohammadi, E. Fatemizadeh, and M.H. Mahoor, “A Bayesian Source Separation Method for Intensity Estimation of Action Units”, In press, IEEE Transactions on Affective Computing.
  3. M. R. Mohammadi, E. Fatemizadeh, M.H. Mahoor, “A Joint Dictionary Learning and Regression Model for Intensity Estimation of Facial AUs”, Journal of Visual Communication and Image Representation, Volume 47, August 2017, Pages 1–9.
  4. Ali Mollahosseini, Behzad Hassani, Michelle J. Salvador, Hojjat Abdollahi, David Chan, Mohammad H. Mahoor, Facial Expression Recognition from the World Wild Web, IEEE conference on Computer Vision and Pattern Recognition Workshops (CVPR’W), Las Vegas, June 2016. http://arxiv.org/abs/1605.03639
  5. Ali Mollahosseini, David Chan, Mohammad H. Mahoor, “Going Deeper in Facial Expression Recognition using Deep Neural Networks”, IEEE Winter Applications of Computer Vision (WACV), 2016 http://arxiv.org/abs/1511.04110
  6. Behzad Hasani and M. H. Mahoor, “Spatio-Temporal Facial Expression Recognition Using Convolutional Neural Networks and Conditional Random Fields”, Face and Gesture Recognition Conference, Workshop, Washington DC, 2017
  7. Behzad Hasani and M. H. Mahoor, “Facial Affect Estimation in the Wild Using Deep Residual and Convolutional Networks”, CVPR workshop, Hawaii, 2017
  8. Behzad Hasani and M. H. Mahoor, “Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks”, CVPR workshop, Hawaii, 2017