Computer classification of facial expressions requires large amounts of data and this data needs to reflect the diversity of conditions seen in real applications. Public datasets help accelerate the progress of research by providing researchers with a benchmark resource. We present a comprehensively labeled dataset of ecologically valid spontaneous facial responses recorded in natural settings over the Internet. To collect the data, online viewers watched one of three intentionally amusing Super Bowl commercials and were simultaneously filmed using their webcam. They answered three self-report questions about their experience. A subset of viewers additionally gave consent for their data to be shared publicly with other researchers. This subset consists of 242 facial videos (168,359 frames) recorded in real world conditions. The dataset is comprehensively labeled for the following: 1) frame-by-frame labels for the presence of 10 symmetrical FACS action units, 4 asymmetric (unilateral) FACS action units, 2 head movements, smile, general expressiveness, feature tracker fails and gender; 2) the location of 22 automatically detected landmark points; 3) self-report responses of familiarity with, liking of, and desire to watch again for the stimuli videos and 4) baseline performance of detection algorithms on this dataset.

Abstract-This paper presents our response to the first international challenge on Facial Emotion Recognition and Analysis. We propose to combine different types of features to automatically detect Action Units in facial images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and an RBF kernel. During the training step, we combine these two types of features using the recently proposed SimpleMKL algorithm. SVM outputs are then averaged to exploit temporal information in the sequence. To evaluate our system, we perform deep experimentations on several key issues: influence of features and kernel function in histogrambased SVM approaches, influence of spatially-independent information versus geometric local appearance information and benefits of combining both, sensitivity to training data and interest of temporal context adaptation. We also compare our results to those of the other participants and try to explain why our method had the best performance during the FERA challenge.

This study presents a combination of geometric and appearance features used to automatically detect Action Units in face images. We use one multi-kernel SVM for each Action Unit we want to detect. The first kernel matrix is computed using Local Gabor Binary Pattern (LGBP) histograms and a histogram intersection kernel. The second kernel matrix is computed from AAM coefficients and a RBF kernel. During the training step, we combine these two type s of features using the recent SimpleMKL algorithm. SVM outputs are then filtered to exploit dynamic relationships between Action Units.