Abstract
Facial action units (AUs) play an important role in human emotion understanding. One big challenge for datadriven AU recognition approaches is the lack of enough AU
annotations, since AU annotation requires strong domain
expertise. To alleviate this issue, we propose a knowledgedriven method for jointly learning multiple AU classifiers
without any AU annotation by leveraging prior probabilities
on AUs, including expression-independent and expressiondependent AU probabilities. These prior probabilities are
drawn from facial anatomy and emotion studies, and are
independent of datasets. We incorporate the prior probabilities on AUs as the constraints into the objective function of
multiple AU classifiers, and develop an efficient learning algorithm to solve the formulated problem. Experimental results on five benchmark expression databases demonstrate
the effectiveness of the proposed method, especially its generalization ability, and the power of the prior probabilities.