About this Research Topic
Nonverbal behaviors such as gaze, facial expressions, gestures, vocal behavior carry significant information regarding a human’s personality, emotions, engagement, intentions, action goals and focus of attention. A large part of human communication takes place nonverbally (and often implicitly) during an explicit exchange of thoughts, attitudes, concerns and feelings. Analyzing basic principles of human communication through nonverbal signals is a long-standing research focus of cognitive and social psychology. However, automatic realization of such analyses, especially by using machine learning, or in general computational techniques is a relatively unexplored avenue, although these techniques can be very efficient and effective.
Automatised detection and analysis of nonverbal social signals can be of particular relevance not only to human-human, but also to human-robot interaction. Over the last decade, much research effort has been dedicated to improving robots’ capabilities regarding perceiving, interacting, and cooperating with humans. Indeed, social human-robot interaction requires augmenting robots’ more standard functionality by the ability to recognize and interpret human social signals, in order to be able to engage naturally and intuitively with a human. Simultaneously, research efforts are being put in examining the human side of the human-robot interaction, namely, the human mechanisms social cognition in interactions with artificial agents (embodied robots specifically). This is crucial in order to understand how the human brain processes social signals carried out by non-human agents, and whether such agents can evoke mechanisms of social cognition in humans. Also in this case, machine learning techniques prove useful to explore patterns of neural and behavioural activity of the human counterparts.
This Research Topic is dedicated to developing computational techniques for analysis of nonverbal social signals in human-human as well as human-robot interaction. Specifically, we focus on machine learning methodologies, but the topics can also cover other computational approaches as well as other types of nonverbal behavior analysis and multi-modal data, in the context of human-human and human-robot interaction analysis. Novel and innovative research papers, reviews, benchmarks, databases, simulation tools or new evaluation methodologies related to the topics given below are all welcome.
The topics of interest include but are not limited to:
- Social Signal Processing
- Emotion Recognition (in-the-wild, individuals or groups)
- Supervised/Unsupervised Machine Learning Models for Nonverbal Behavior Understanding
- Deep Learning Approaches for Nonverbal Behavior Analysis
- Computational modeling of mechanisms of social cognition
- Cooperation/competition in joint tasks
- Social signals in joint action
- Mechanisms of social cognition (joint attention, spatial perspective taking, action prediction, theory of mind) in human-human or human-robot interaction
- Neural correlates of mechanisms of social cognition
- Inference of intentions from behaviour (e.g. for Social Robotics)
- Automatic Human Social Behavior Understanding for Developmental Robotics
- Real-time Recognition of Gaze, Gestures, Affect, Facial Expressions, etc.
- Interactive and Active Learning for Social Robotics
- Transfer Learning for Human-Human and Human-Robot Interactions
- Affective Human-Robot Interaction
- Affective Human-Robot Collaboration
- Human-Robot Engagement Prediction
- Socially Assistive Human-Robot Interactions (e.g. for Heath, Education, Entertainment, Business)
- Interactional Synchrony Between Human and Social Robots
- Emotion-aware Robots
- Personality-aware Robots
- Human-Robot Interaction Styles
- Multimodal Expression of Emotion by Virtual Characters/Robots During Affective Interaction with Users
Keywords: Nonverbal Behavior, Social Robots, Multimodal Data Analysis, Machine Learning, Social Interactions
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.