The development of a two-stage approach for appraisal inference from automatically detected Action Unit (AU) intensities in recordings of human faces is described. AU intensity estimation is based on a hybrid approach fusing information from an individually fitted mesh model of the faces and texture information. Evaluation results for two datasets and a comparison against a state-of-the-art system, namely OpenFace are provided. In the second stage, the emotional appraisals novelty, valence and control are predicted from estimated AU intensities by linear regressions. Prediction performance is evaluated based on face recordings from a market research study, which were rated by human observers in terms of perceived appraisals. Predictions of valence and control from automatically estimated AU intensities closely match those obtained from manually coded AUs in terms of agreement with human observers, while novelty predictions lag somewhat behind. Overall, results highlight the flexibility and interpretability of a two-stage approach to emotion inference.

Over the last few decades, there has been an increasing call in the field of computer vision to use machine-learning techniques for the detection, categorization, and indexing of facial behaviors, as well as for the recognition of emotion phenomena. Automated Facial Expression Analysis has become a highly attractive field of competition for academic laboratories, startups and large technology corporations. This paper introduces the new Actor Study Database to address the resulting need for reliable benchmark datasets. The focus of the database is to provide real multi-view data, that is not synthesized through perspective distortion. The database contains 68-minutes of high-quality videos of facial expressions performed by 21 actors. The videos are synchronously recorded from five different angles. The actors' tasks ranged from displaying specific Action Units and their combinations at different intensities to enactment of a variety of emotion scenarios. Over 1.5 million frames have been annotated and validated with the Facial Action Coding System by certified FACS coders. These attributes make the Actor Study Database particularly applicable in machine recognition studies as well as in psychological research into affective phenomena-whether prototypical basic emotions or subtle emotional responses. Two state-of-the-art systems were used to produce benchmark results for all five different views that this new database encompasses. The database is publicly available for non-commercial research.

A novel system for facial expression recognition is presented. It is designed to assess valence (positive or negative feeling) in the context of market research applications. Other design parameters that were met are real-time capability and robust results even when using off-the-shelf equipment (standard web cam and lighting). The paper further presents an empirical study that attests the system satisfying predictive validity for market research applications as long as very small absolute valence values close to zero are not interpreted.

Simple lexicographic decision heuristics that consider cues one at a time in a particular order and stop searching for cues as soon as a decision can be made have been shown to be both accurate and frugal in their use of information. But much of the simplicity and success of these heuristics comes from using an appropriate cue order. For instance, the Take The Best heuristic uses validity order for cues, which requires considerable computation, potentially undermining the computational advantages of the simple decision mechanism. But many cue orders can achieve good decision performance, and studies of sequential search for data records have proposed a number of simple ordering rules that may be of use in constructing appropriate decision cue orders as well. Here we consider a range of simple cue ordering mechanisms, including tallying, swapping, and move-to-front rules, and show that they can find cue orders that lead to reasonable accuracy and considerable frugality when used with lexicographic decision heuristics.