A first evaluation study of a database of kinetic facial expressions (DaFEx)

Abstract

In this paper we present DaFEx (Database of Facial Expressions), a database created with the purpose of providing a benchmark for the evaluation of the facial expressivity of Embodied Conversational Agents (ECAs). DaFEx consists of 1008 short videos containing emotional facial expressions of the 6 Ekman's emotions plus the neutral expression. The facial expressions were recorded by 8 professional actors (male and female) in two acting conditions ("utterance" and "no-utterance") and at 3 intensity levels (high, medium, low). The properties of DaFEx were studied by having 80 subjects classify the emotion expressed in the videos. High rates of accuracy were obtained for most of the emotions displayed. We also tested the effect of the intensity level, of the articulatory movements due to speech, and of the actors' and subjects' gender, on classification accuracy. The results showed that decoding accuracy decreases with the intensity of emotions; that the presence of articulatory movements negatively affects the recognition of fear, surprise and of the neutral expression, while it improves the recognition of anger; and that facial expressions seem to be recognized (slightly) better when acted by actresses than by actors.

Evaluation of a Facial Animation Authoring Pipeline Seamlessly Supporting Performance Capture and Manual Key-pose Editing

“…Our subjects recognized pretty wrongly the disgust dimension (J=0.438). All the other results match with the results claimed in [27], who evaluated their reference videos on 80 subjects. Quoting [27]: "anger seems to be the emotion which is best recognized, [...].…”

“…In our work, we exploit emotion transfer to evaluate the retargeting. Also Battocchi [27] and Costantini et al [28] used emotion judgment as mean of evaluation. However, as shown in [27], even if a professional actor perform the emotions, subjects falls into misinterpretation.…”

“…Also Battocchi [27] and Costantini et al [28] used emotion judgment as mean of evaluation. However, as shown in [27], even if a professional actor perform the emotions, subjects falls into misinterpretation. As great as an actor can be in conveying a certain emotion through a facial expression, there are no guarantees that the emotion is correctly perceived.…”

“…The six reference videos, displaying the six Ekman's emotions [1], belong to the DaFEx database of dynamic facial expressions [27] (Actor 1, high intensity). The videos show a professional female actress.…”

Affective Web Service Design

“…In designing Web applications (e.g., ecommerce applications) that carry out a certain set of goals for human users, such as purchase orders, the importance of the affects of such applications has already been put forward to system designers' attention (e.g., [24,12]). Therefore, there has been much research into evaluating human emotions [11,6], expressing emotions [17,4], and the effectiveness of such approaches to improving human-computer interactions [16,5,3,25]. Business communities also have been aware of the significance of customer satisfaction in measuring business performances (e.g., American Consumer Satisfaction Index [1]) because for most companies, repeat customers are major contributors to profit [1].…”