The affective facial recognition task: The influence of cognitive styles and exposure times

Peng, Shuna; Dong, Yang; Wang, Weisha; Hu, Jieyi; Dong, Wei-Yang

doi:10.1016/j.jvcir.2019.102674

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent years have witnessed an increasing number of studies targeting human-human dyadic interaction analysis, thanks to the wide application scenarios -such as, among others, surveillance, transportation, health, information security, and intelligent human agent interaction -and the advancement of pattern recognition, cognitive science, and neural networks [16]. Past works [6,19,21,22,25] have investigated the problem of automatically generating an appropriate response or reaction for a given input.…”

Section: Introductionmentioning

confidence: 99%

Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?

Song¹,

Spitale²,

Luo³

et al. 2023

Preprint

View full text Add to dashboard Cite

According to the Stimulus Organism Response (SOR) theory, all human behavioral reactions are stimulated by context, where people will process the received stimulus and produce an appropriate reaction. This implies that in a specific context for a given input stimulus, a person can react differently according to their internal state and other contextual factors. Analogously, in dyadic interactions, humans communicate using verbal and nonverbal cues, where a broad spectrum of listeners' nonverbal reactions might be appropriate for responding to a specific speaker behaviour. There already exists a body of work that investigated the problem of automatically generating an appropriate reaction for a given input. However, none attempted to automatically generate multiple appropriate reactions in the context of dyadic interactions and evaluate the appropriateness of those reactions using objective measures. This paper starts by defining the facial Multiple Appropriate Reaction Generation (fMARG) task for the first time in the literature and proposes a new set of objective evaluation metrics to evaluate the appropriateness of the generated reactions. The paper subsequently introduces a framework to predict, generate, and evaluate multiple appropriate facial reactions.

show abstract