Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiaotian Li, Xiang Zhang, Taoyue Wang, Lijun Yin, | Summary: Recent studies on the automatic detection of facial action unit (AU) have extensively relied on large-sized annotations. However, manually AU labeling is difficult, time-consuming, and costly. Most existing semi-supervised works ignore the informative cues from the temporal […]
Continue.. Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels