Skip to main content
. Author manuscript; available in PMC: 2018 Jul 1.
Published in final edited form as: Int J Comput Vis. 2017 Feb 9;123(3):372–391. doi: 10.1007/s11263-017-0989-7

Fig. 7.

Fig. 7

Results on discovering common facial actions: (a) Facial features extracted from the tracked points. (b) An example of common discovered facial events (indicated by dashed-line rectangles). (c)(d) Accuracy evaluation on precision-recall and average precision (AP).