Skip to main content
. Author manuscript; available in PMC: 2019 Jun 26.
Published in final edited form as: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2018 Dec 17;2018:2090–2099. doi: 10.1109/CVPR.2018.00223

Figure 3.

Figure 3.

Illustration of the learned W with different λ on real data of AU12. Each sample is colored by cluster ID (left column) or weak-annotations, i.e., positive v.s. negative (right column). Parentheses indicate the % of agreement between WSC re-annotation and ground truth (higher better). A good balance is found at λ = 2−4 where WSC achieved highest agreement.