Kostas Karpouzis

Affect-sensitive systems such as social robots and virtual agents are increasingly being investigated in real-world settings. In order to work effectively in natural environments, these systems require the ability to infer the affective and mental states of humans and to provide appropriate timely output that helps to sustain long-term interactions. This special issue, which appears in two parts, includes articles on the design of socio-emotional behaviors and expressions in robots and virtual agents and on computational approaches for the automatic recognition of social signals and affective states.

A vital requirement for social robots and virtual agents is the ability to perceive and interpret social, affective expressions and states of humans, so as to be able to engage in and behave appropriately during sustained social interactions [1, 2]. Examples include ensuring that the user is interested in maintaining the interaction or providing suitable empathic responses. A fundamental component in these “mentalising” and “empathising” capabilities is the interpretation of human behaviour [3] from sensory input, which must be conducted ...

In this paper, we address the problem of 3d motion and structure estimation of 3d objects appearing in 2d images; namely, the estimation of the parameters of 3d motion, such as rotation and translation in 3d space, and the third dimension of certain objects that can be seen in a time sequence of 2d images. The study of the problem

Processing of recorded or real-time signals, feature extraction, and recognition are concepts of utmost important to an affect–aware and capable system, since they offer the opportunity to machines to benefit from modeling human behavior based on theory and interpret it based on observation. This chapter discusses feature extraction and recognition based on unimodal features in the case of speech, facial expressions and gestures, and physiological signals and elaborates on attention, fusion, dynamics, and adaptation in different ...

Even though current multi-user virtual environments enjoy the advanced potential of desktop computers with respect to processing and displaying 3D graphics, they distinctively lack the essential quality to make them more appealing to less technologysavvy or handicapped individuals and, thus, replace or at least challenge, conventional communications systems.

Rendering and Analysis.- Simulation Level of Detail for Virtual Humans.- Towards Natural Gesture Synthesis: Evaluating Gesture Units in a Data-Driven Approach to Gesture Synthesis.- 3D Audiovisual Rendering and Real-Time Interactive Control of Expressivity in a Talking Head.- Semantic Segmentation of Motion Capture Using Laban Movement Analysis.- Culture and Identity.- A Computational Model of Culture-Specific Conversational Behavior.- Ethnic Identity and Engagement in Embodied Conversational Agents.- Neuroticism - A Competitive Advantage (Also) for IVAs?.- Behavior Models.- Emotionally Expressive Head and Body Movement During Gaze Shifts.- Fuzzy Similarity of Facial Expressions of Embodied Agents.- The Behavior Markup Language: Recent Developments and Challenges.- Dynamic Behavior Qualifiers for Conversational Agents.- Feedback Models.- Creating Rapport with Virtual Agents.- Incremental Multimodal Feedback for Conversational Agents.- Searching for Prototypical Facial Feedback Signals.- Fluid Semantic Back-Channel Feedback in Dialogue: Challenges and Progress.- Dialogues.- T2D: Generating Dialogues Between Virtual Agents Automatically from Text.- So Let's See: Taking and Keeping the Initiative in Collaborative Dialogues.- Applications.- Health Document Explanation by Virtual Agents.- Virtual Patients for Clinical Therapist Skills Training.- Integrating a Virtual Agent into the Real World: The Virtual Anatomy Assistant Ritchie.- Proactive Authoring for Interactive Drama: An Author's Assistant.- Evaluation.- The Effects of an Embodied Conversational Agent's Nonverbal Behavior on User's Evaluation and Behavioral Mimicry.- Spatial Social Behavior in Second Life.- Generating Embodied Descriptions Tailored to User Preferences.- Gaze Models.- Scrutinizing Natural Scenes: Controlling the Gaze of an Embodied Conversational Agent.- Attentive Presentation Agents.- The Rickel Gaze Model: A Window on the Mind of a Virtual Human.- Emotions.- Embodied Creative Agents: A Preliminary Social-Cognitive Framework.- Feel the Difference: A Guide with Attitude!.- It's All in the Anticipation.- Incorporating Emotion Regulation into Virtual Stories.- Poster Session.- Endowing Emotional Agents with Coping Strategies: From Emotions to Emotional Behaviour.- From IVAs to Comics Generating Comic Strips from Emergent Stories with Autonomous Characters.- Emotional Agents with Team Roles to Support Human Group Training.- Context Awareness in Mobile Relational Agents.- Implicit Training of Virtual Agents.- Human Actors and Virtual Agents Playing Together to Transform Stage Direction Practices.- Towards Characters with a Full Episodic Memory.- Towards Fast Prototyping of IVAs Behavior: Pogamut 2.- Towards a Multicultural ECA Tour Guide System.- Towards the Specification of an ECA with Variants of Gestures.- AI-RPG Toolkit: Towards A Deep Model Implementation for Improvisational Virtual Drama.- Attention Based, Naive Strategies, for Guiding Intelligent Virtual Agents.- Behavioural Reactive Agents for Video Game Opponents with Personalities.- Adapting Hierarchical Social Organisation by Introducing Fear into an Agent Architecture.- Roles of a Talking Head in a Cooperative Human-Robot Dialogue System.- Modeling Imitational Behavior Via Social Comparison Theory.- Social Animation in Complex Environments.- A Script Driven Multimodal Embodied Conversational Agent Based on a Generic Framework.- A Quiz Game Console Based on a Generic Embodied Conversational Agent Framework.- AVSML: An XML-Based Markup Language for Web Information Integration in 3D Virtual Space.- Simulation Environment for Anticipatory Behaving Agents from the Artificial Life Domain.- Towards an Architecture for Aligned Speech and Gesture Production.- Avatar Puppetry Using Real-Time Audio and Video Analysis.- Double Appraisal for Synthetic Characters.- An Expressive Avatar for Instant Messaging Endowed with Emotional Intelligence.- ALICIA.- Towards a Unified Model of Social and Environment-Directed Agent Gaze Behaviour.- Automatic Generation of Expressive Gaze in Virtual Animated Characters: From Artists Craft to a Behavioral Animation Model.- Analyzing Gaze During Face-to-Face Interaction.- Affect and Metaphor in an ICA: Further Developments.- A Case-Based Approach to Intelligent Virtual Agent's Interaction Experience Representation.- Modeling Spatiotemporal Uncertainty in Dynamic Virtual Environments.- Industrial Demos.- Avatars Contributions to Commercial Applications with Living ActorTM Technology.- The CereVoice Characterful Speech Synthesiser SDK.- VirtuOz Interactive Agents.- Finger Tracking for Virtual Agents.- Techniques of Dialogue Simulation.

Abstract. In this work, we explore the relation between expressive head movement and user profile information in game play settings. Facial gesture analysis cues are statistically correlated with players' demographic characteristics in two different settings, during game-play and at events of special interest (when the player loses during game play). Experiments were conducted on the Siren database, which consists of 58 participants, playing a modified version of the Super Mario. Here, as player demographics are considered the gender and ...

▪ User models for game play o Modelling prototypical player and non-player characters o Emotion and games: inducing and expressing emotions o Requirements for natural and intuitive interfaces o User, environment and interaction context o Modelling and measuring player satisfaction o Player-adapted content creation (eg opponents for individual players)

face recognition and syntheticnatural hybrid coding tool involving frontal and profile views is presented in this paper. The tool utilizes the above mentioned 2D images upon which certain protuberant points are automatically detected and adapts a generic 3D head model (polygon mesh) according to the predetermined information gained by the available views. This mesh provides shape information which combined with texture information is important for the robustness of a recognition system. The main advantage of the proposed approach ...

This paper presents the modules that comprise a sign generation tool for Greek Sign Language (GSL). The tool combines Natural Language (NL) knowledge with avatar technology in order to allow for unrestricted generation of sign utterances. The NL knowledge of the system is exploited in the context of typical NLP procedures, which involve syntactic parsing of linguistic strings as well as structure and lexicon mapping according to standard Machine Translation (MT) practices. The coding on linguistic strings which are ...

Abstract: The LearningByDoing eClassroom© is a highly structured synchronous application for teaching and doing research on medium to large sized groups over the Internet and is an open system for content delivery. Forty students, four facilitators, and a principle instructor can successfully co-create an environment, which processes interactions similar to F2F classes, but without the apparent need, nor access to, traditional non-verbal social cues. The structure of the LearningByDoing eClassroom© was designed and developed over the ...