11 Oct 2010: Location information added
8 Sep 2010: Preliminary program added
10 Jun 2010: Deadline extended to 17 Jun 2010
27 May 2010: Keynote speaker details added
24 May 2010: Journal special issue details added
A vital requirement for social robots, virtual agents, and
human-centered multimedia interfaces is the ability to infer the
affective and mental states of humans and provide appropriate, timely
output during sustained social interactions. Examples include ensuring
that the user is interested in maintaining the interaction or providing
suitable empathic responses through the display of facial expressions,
gestures, or generation of speech.
This workshop will cover real-time computational techniques for the
recognition and interpretation of human multimodal verbal and non-verbal
behaviour, models of mentalising and empathising for interaction, and
multimedia techniques for synthesis of believable social behaviour
supporting human-agent and human-robot interaction.
A key aim of the workshop is the identification and investigation of
important open issues in real-time, affect-aware applications 'in the
wild' and especially in embodied interaction, i.e. with robots and
embodied conversational agents. Issues such as natural and multimodal
interaction, estimation and adaption to context, context dependent
processing and related databases, HCI/HRI beyond emotion (cognition,
behaviour, etc.), and best practices for applications in real
environments will be discussed in the context of interacting with
other humans and social artefacts.
We welcome the participation of researchers from diverse fields,
including signal processing and pattern recognition, machine learning,
cognition, affective science, human-computer interaction, human-robot
interaction, and robotics. We hope an interdisciplinary group will
benefit from mutual osmosis of ideas, concepts and developments in the
field.
The workshop especially welcomes studies that provide new insights into
the use of multimodal and multimedia techniques for enabling interaction
between humans, robots, and virtual agents in naturalistic settings. We
also encourage the submission of work-in-progress papers including
recent results providing novel and exciting contributions.
Accepted workshop papers will be published in the ACM Digital Library.
As a follow-up to the workshop, there will be a special issue on Affective
Interaction in Natural Environments in the ACM Transactions on Interactive
Intelligent Systems (TiiS). Participation in the AFFINE
2010 workshop should help interested authors to prepare strong
journal-length submissions to this special issue; but the special issue will
be open to all researchers worldwide who have done relevant work.
Workshop topics may include, but are not limited to:
- Multimedia expression generation in robots and virtual agents,
including:
- Gaze
- Gesures
- Facial Expressions
- Speech
- Other modalities
- Multimodal human affect and social behaviour recognition, including:
- Facial expressions
- Body language
- Speech
- Physiological
- Other modalities
- Perception-action loops in agents/robots
- Cognitive and affective 'mentalising'
- Visual attention / user engagement with robots and embodied conversational agents (ECAs)
- Emotion and cognitive state representation
- Social context awareness and adaptation
- Natural Human-Robot Interaction (HRI) / Human-Computer Interaction (HCI)
- Multimedia HCI
- Multimodal and emotional corpora (naturally evoked or induced emotion)
- Recognition of human behaviour for implicit tagging
- Contributions to standards for multimodal interaction and specification of mark-up languages
as a workshop topic
- Applications to interactive games, robots and virtual agents
This workshop follows the previous successful AFFINE workshops organised
as satellite events of
ICMI '08 and
ICMI-MLMI '09, as well as a special session
organised at
WIAMIS '09. This
is the first time the workshop has been held at ACM Multimedia. AFFINE has a
track record for attracting researchers from the virtual agents, social robotics
and affective computing communities and encourages interdisciplinarity - submissions
from other domains are very welcome.
- Deadline for paper submission: 17 June 2010 (extended)
- Notification of acceptance: 10 July 2010
- Camera ready paper: 18 July 2010
Please prepare your paper in accordance with the
ACM Multimedia Full Paper Guidelines. Your paper may be either 4 or
6 pages in length, including references and figures.
Authors may submit a pdf version of their paper via the ACM Multimedia
EDAS paper submission system. Please note: The review process is
double-blind, so please be sure to remove any identifying information
before uploading your submission (name, affiliation, tell-tale
references, etc).
If you have any questions, please write to the organisers: affine2010 at googlemail dot com
The workshop will be held at the
Plazzo dei Congressi, the
same venue for the main conference. The room number is: Adua 2F Affari.
Aside from the keynote, all presentations are 15 minutes each, and
questions are in panel format at the end of each session with all
authors in a group, in order to faciliate discussion.
Exact coffee break times to be determined
- 9:00-9:15 Welcome and Introduction
- 9:15-10:00 Keynote address (Chair: Ginevra Castellano)
"Automated Analysis of Non-Verbal Affective and Social Behaviour"
(Prof. Antonio Camurri, University of Genoa)
- 10:00-11:15 Morning Session 1
Analysis and recognition (Chair: Louis-Philippe Morency)
- "Enjoyment Recognition from Physiological Data in a Car Racing Game"
(Tognetti, S., Garbarino, M., Bonanno, A. T., Bonarini, A., and
Matteucci, M.)
- "RANSAC-based Training Data Selection for Emotion Recognition from
Spontaneous Speech"
(Bozkurt, E., Erdem, C. E., Erzin, E., and
Erdem, T.)
- "Genetic Search Feature Selection for Affective Modeling: a Case
Study on Reported Preferences"
(Perez-Martinez, H., and Yannakakis,
G.)
- "Real Time Labeling of Affect in Music Using the AffectButton"
(Broekens, J., Pronker, A., and Neuteboom, M.)
- Questions panel with all authors
- 11:15-11:45 Coffee Break
- 11:45-13:00 Morning Session 2
Synthesis and generation (Chair: Christopher Peters)
- "Synthesizing Expressions using Facial Feature Point Tracking: How
Emotion is Conveyed"
(Baltrusaitis, T., Riek, L. D., and Robinson,
P.)
- "Selecting Appropriate Agent Responses based on Non-Content
Features"
(ter Maat, M., and Heylen, D.)
- "Interpretation of Emotional Body Language Displayed by Robots"
(Beck, A., Hiolle, A., Mazel, A., and Canamero, L.)
- Questions panel with all authors
- 13:00-14:30 Lunch break
- 14:30-16:00 Afternoon Session 1
Interaction (1) (Chair: Laurel Riek)
- "Closing the Loop: from Affect Recognition to Empathic Interaction"
(Leite, I., Pereira, A., Mascarenhas, S., Castellano, G., Martinho, C.,
Prada, R., and Paiva, A.)
- "Designing Affective Computing Learning Companions with Teachers as
Design Partners"
(Girard, S., and Johnson, H.)
- "Ubiquitous Social Perception Abilities for Interaction Initiation
in Human-Robot Interaction"
(Deshmukh, A., Castellano, G., Lim, M.Y., Aylett, R., and McOwan, P. W.)
- "A Motivational Health Companion in the Home as Part of an
Intelligent Health Monitoring Sensor Network"
(Evers, V., and
Krose, B.)
- "Interpreting non-linguistic utterances by robots: studying the
influence of physical appearance"
(Read, R.G., and Belpaeme, T.)
- Questions panel with all authors
- 16:00-16:15 Coffee Break
- 16:15-18:00 Afternoon Session 2
Interaction (2) (Chair: Ginevra Castellano)
- "On the Importance of Eye Gaze in a Face-to-Face Collaborative Task"
(Fagel, S., and Bailly, G.)
- "Use of Nonverbal Speech Cues in Social Interaction between Human
and Robot: Emotional and Interactional markers"
(Delaborde, A., and Devillers, L.)
- "Facilitative Effects of Communicative Gaze and Speech in
Human-Robot Cooperation"
(Boucher, J.-D., Ventre-Dominey, J., Fagel, S., Bailly, G., and Dominey,
P. F.)
- "Can Polite Computers Produce Better Human Performance?"
(Wu, P.)
- "Augmented Photoware Interfaces for Affective Human-Human
Interactions"
(Vatavu, R. D.)
- Questions panel with all authors
Organising Committee (alphabetical)
- Ginevra Castellano, Queen Mary University London, UK
- Kostas Karpouzis, National Technical University of Athens, Greece
- Jean-Claude Martin, LIMSI-CNRS, France
- Louis-Philippe Morency, University of Southern California, USA
- Christopher Peters, Coventry University, UK
- Laurel Riek, University of
Cambridge, UK
Program Committee (alphabetical)
- Aris Alissandrakis (ATR, Japan)
- Elisabeth André (Augsburg Universtiy, Germany)
- Elisabetta Bevacqua (CNRS/TELECOM ParisTech, France)
- Tony Belpaeme (University of Plymouth, UK)
- Timothy Bickmore (Northeastern University, USA)
- Nadia Bianchi-Berthouze (University College London, UK)
- Carlos Busso (The University of Texas at Dallas, USA)
- Lola Cañamero (University of Hertfordshire, UK)
- Marc Cavazza (University of Teesside, UK)
- Kerstin Dautenhahn (University of Hertfordshire, UK)
- Vanessa Evers (University of Amsterdam, Netherlands)
- Hatice Gunes (Imperial College, UK)
- Dirk Heylen (University of Twente, Netherlands)
- Stefanos Kollias (National Technical University of Athens, Greece)
- Maurizio Mancini (University of Genova, Italy)
- Carlos Martinho (Instituto Superior Técnico, Portugal)
- Peter William McOwan (Queen Mary University of London, UK)
- Yukiko Nakano (Seikei University, Japan)
- Anton Nijholt (University of Twente, Netherlands)
- Maja Pantic (Imperial College London, UK / University of Twente,
Netherlands)
- Catherine Pelachaud (CNRS/TELECOM ParisTech, France)
- Peter Robinson (University of Cambridge, UK)
- Marc Schroeder (DFKI, Germany)
- Bjoern Schuller (Technische Universitaet Muenchen, Germany)
- Candace Sidner (Worcester Polytechnic Institute, USA)
- Gualtiero Volpe (University of Genova, Italy)
- Astrid Weiss (University of Salzburg, Austria)
- Yorick Wilks (University of Oxford, UK)
- Georgios Yannakakis (University of Copenhagen, Denmark)
- Massimo Zancanaro (FBK, Italy)
Photo by Frank Kovalchek