Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization

@inproceedings{Ruiz2014RegularizedMM,
  title={Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization},
  author={Adria Ruiz and Joost van de Weijer and Xavier Binefa},
  booktitle={BMVC},
  year={2014}
}
Introduction: Most efforts in facial behavior analysis have focused on proposing supervised methods to detect a set of predefined gestures such as the Action Units. However, supervised AU detection is a difficult task which requires a huge labelling effort to annotate spontaneous behavior databases. In contrast, we focus on a different problem which we call facial behavior categorization. The goal is to estimate high-level semantic labels for videos of recorded people by means of analysing… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 11 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

Affectivamit facial expression dataset (am-fed): Naturalistic and spontaneous facial expressions collected in-the-wild

  • D. McDuff, R. Kaliouby, T. Senechalz, M. Amrz, J. F. Cohn, R. Picard
  • In Computer Vision and Pattern Recognition…
  • 2013
1 Excerpt

Similar Papers

Loading similar papers…