Perception of Blended Emotions: From Video Corpus to Expressive Agent

Buisine, Stéphanie; Abrilian, Sarkis; Niewiadomski, Radosław; Martin, Jean‐Claude; Devillers, Laurence; Pélachaud, Catherine

doi:10.1007/11821830_8

Cited by 29 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a multimodal corpus exploratory approach, Buisine et al [5] defined a method for replaying annotated gestures and facial expressions. The authors describe an experimental study exploring how subjects perceive different replays but do not compare how facial and postural expressions are perceived individually vs. jointly.…”

Section: Nonverbal Expression Of Emotion In Virtual Charactersmentioning

confidence: 99%

Combining Facial and Postural Expressions of Emotions in a Virtual Character

Clavel

Plessier²,

Martin

et al. 2009

Intelligent Virtual Agents

Self Cite

View full text Add to dashboard Cite

Abstract. Psychology suggests highly synchronized expressions of emotion across different modalities. Few experiments jointly studied the relative contribution of facial expression and body posture to the overall perception of emotion. Computational models for expressive virtual characters have to consider how such combinations will be perceived by users. This paper reports on two studies exploring how subjects perceived a virtual agent. The first study evaluates the contribution of the facial and postural expressions to the overall perception of basic emotion categories, as well as the valence and activation dimensions. The second study explores the impact of incongruent expressions on the perception of superposed emotions which are known to be frequent in everyday life. Our results suggest that the congruence of facial and bodily expression facilitates the recognition of emotion categories. Yet, judgments were mainly based on the emotion expressed in the face but were nevertheless affected by postures for the perception of the activation dimension.Keywords: evaluation of virtual agents, affective interaction, conversational and non-verbal behavior, multimodal interaction with intelligent virtual agent

show abstract

Section: Nonverbal Expression Of Emotion In Virtual Charactersmentioning

confidence: 99%

Combining Facial and Postural Expressions of Emotions in a Virtual Character

Clavel

Plessier²,

Martin

et al. 2009

Intelligent Virtual Agents

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the animation displaying a simple expression was perceived as the closest to the original by 33% of the participants in the audio condition, and by 61% of the participants in the no audio condition (see Table 2). Comparing two animations of complex facial expressions the one generated with our model of complex facial expressions received 17% (audio) and 9% (no audio condition) in turn while the manually defined complex facial expressions were better in this test (24% and 20%) (see Buisine et al, 2006 for detailed results).…”

Section: Discussionmentioning

confidence: 83%

Affect expression in ECAs: Application to politeness displays

Niewiadomski

Pélachaud

2010

International Journal of Human-Computer Studies

Self Cite

View full text Add to dashboard Cite

“…synthesising head position and eye gaze is also presented in the paper. Objective evaluation was offered via the "copy-synthesis" method Buisine et al [2006], where synthesised movies are subjectively compared with hand crafted animation. Results indicate that the automatic approach is "satisfactory" and that participants were able to identify at least some of the expressions displayed.…”

Section: Concatenative Approachesmentioning

confidence: 99%