Deep Structure Inference Network for Facial Action Unit Recognition

@inproceedings{Corneanu2018DeepSI,
  title={Deep Structure Inference Network for Facial Action Unit Recognition},
  author={Ciprian A. Corneanu and Meysam Madadi and Sergio Escalera},
  booktitle={ECCV},
  year={2018}
}
FOR FACIAL ACTION UNIT RECOGNITION CIPRIAN CORNEANU, MEYSAM MADADI, SERGIO ESCALERA PROBLEM Facial expressions are combinations of basic basic patterns of muscular activation called Action Units (AU). Recognizing AUs is key for general facial expression analysis. Patch Learning. AUs modify facial morphology locally. One could predict specific AUs from informative face regions selected depending on the facial geometry. Structure Learning. Several AUs can be active at the same time and certain AU… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 27 references

Joint patch and multi-label learning for facial action unit detection

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 2 Excerpts
Highly Influenced

Deep Region and Multi-label Learning for Facial Action Unit Detection

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016

Deep learning the dynamic appearance and shape of facial action units

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) • 2016

Similar Papers

Loading similar papers…