Patrick Lucey

TL;DR: The Cohn-Kanade (CK+) database is presented, with baseline results using Active Appearance Models (AAMs) and a linear support vector machine (SVM) classifier using a leave-one-out subject cross-validation for both AU and emotion detection for the posed data.

TL;DR: A major factor hindering the deployment of a fully functional automatic facial expression detection system is the lack of representative data, so enough data is available to build robust models so high performance can be gained.

TL;DR: In this article, an active appearance model (AAM)-based system was proposed to automatically detect the frames in video in which a patient is in pain, which can deal with these movements and can achieve significant improvements in both the AU and pain detection performance compared to the current state-of-the-art approaches which utilize similarity-normalized appearance features only.

TL;DR: An active appearance model (AAM)-based system that can automatically detect the frames in video in which a patient is in pain is described and can achieve significant improvements in both the AU and pain detection performance compared to the current-state-of-the-art approaches which utilize similarity-normalized appearance features only.

TL;DR: To promote and facilitate research into pain and augmentcurrent datasets, a portion of this database, which includes 200 sequences across 25 subjects, containing more than 48,000 coded frames of spontaneous facial expressions with 66-point AAM tracked facial feature landmarks, is publicly made available.