Personal tools
You are here: Home SIGs and LIGs Speech SIG EmoSPACE


1st International Workshop on Emotion Synthesis, rePresentation, and Analysis in Continuous spaces (EmoSPACE) In conjunction with the IEEE FG 2011 Santa Barbara, 24 March, 2011

1st International Workshop on Emotion Synthesis, rePresentation, and Analysis in Continuous spacE (EmoSPACE)
In conjunction with the IEEE FG 2011
Santa Barbara, 21. March, 2011

Submission closed...:

Call for Papers

Human affective behaviour is multimodal, continuous and complex. Despite major advances within the affective computing research field, modelling, analysing, interpreting and responding to human affective behaviour still remains as a challenge for automated systems as emotions are complex constructs, with fuzzy boundaries and with substantial individual variations in expression and experience. Therefore, affective and behavioural computing researchers have recently invested increased effort in exploring how to best model, analyse and interpret the subtlety, complexity and continuity of affective behaviour in terms of latent dimensions and appraisals, rather than in terms of a small number of discrete emotion categories.

The key aim of this workshop is to present cutting-edge research and new challenges in automatic, dimensional and continuous analysis and synthesis of human emotional behaviour in an interdisciplinary forum of affective and behavioural scientists. More specifically, the workshop aims (i) to bring forth existing efforts and major accomplishments in modelling, analysis and synthesis of emotional expressions in dimensional and continuous spaces, (ii) while encouraging the design of novel applications in context as diverse as human-computer and human-robot interaction, clinical and biomedical studies, learning and driving environments, and entertainment technology, and (iii) to focus on open issues and new challenges in the field. The workshop will also bring together two Keynote Speakers who are leading experts in modelling and analysis of naturalistic emotions in dimensional and continuous spaces.

Suggested workshop topics include, but are by no means limited to:
  • Modalities and cues for dimensional emotion recognition
    • facial expressions
    • head movements and gestures
    • body postures and gestures
    • audio (e.g., speech, non-linguistic vocalisations, etc.)
    • bio signals (e.g., heart, brain, thermal signals, etc.)
  • Automatic analysis and prediction
    • approaches for discretised and continuous prediction of emotions
    • identifying appropriate classification and prediction methods
    • introducing or identifying optimal strategies for fusion
    • techniques for modelling high inter-subject variation
    • approaches to determining duration of emotions for automatic analysis
  • Data acquisition and annotation
    • elicitation of emotions
    • individual variations (interpersonal and cognitive issues)
    • (multimodal) naturalistic data sets annotated in dimensional spaces
    • (multimodal) annotation tools for dimensional emotions
    • modelling annotations from multiple raters and their reliability
  • Applications
    • interaction with robots, virtual agents, and games (including tutoring)
    • single and multi-user smart environments (e.g., in a car)
    • implicit (multimedia) tagging
    • clinical and biomedical studies (e.g., autism, depression, pain etc.)

Workshop Organisers:

Program Committee:

  • Elisabeth André, University of Augsburg, Germany
  • Anton Batliner, FAU Erlangen-Nuremberg, Germany
  • Nadia Bianchi-Berthouze, University College London, UK
  • Felix Burkhardt, Deutsche Telekom, Germany
  • Antonio Camurri, University of Genova, Italy
  • Jeffrey Cohn, University of Pittsburgh, USA
  • Ginevra Castellano, Queen Mary University of London, UK
  • Sidney D'Mello, University of Memphis, USA
  • Eva Hudlicka, Psychometrix Associates, USA
  • Kostas Karpouzis, National Technical University of Athens, Greece
  • Dana Kulic, University of Waterloo, Canada
  • Louis-Philippe Morency, University of Southern California, USA
  • Shrikanth Narayanan, University of Southern California, USA
  • Anton Nijholt, University of Twente, Netherlands
  • Catherine Pelachaud, CNRS, France
  • Thierry Pun, University of Geneva, Switzerland
  • Peter Robinson, University of Cambridge, UK
  • YingLi Tian, City University of New York, USA
  • Khiet Truong, University of Twente, The Netherlands
  • Michel Valstar, Imperial College London, UK
  • Stefanos Zafeiriou, Imperial College London, UK

Important Dates:

Paper Submission: 30 December 2010 (extended)
Notification of Acceptance: 12 January 2011
Camera Ready Paper: 19 January 2011
Workshop: 21 March 2011

Final Technical Program:

09.15-09.30 Introduction

09.30-10.10 Keynote 1 (Chair: Hatice Gunes, Imperial College London)
Alternative Theoretical Perspectives on Emotion Representation and Modeling

Over the past 10 years, three dominant theoretical perspectives have emerged in affective computing, based on emotion research in psychology: the discrete/categorical, the dimensional, and the componential. These perspectives provide theoretical foundations for the core areas of affective computing: emotion recognition, emotion modeling, and emotion expression by synthetic agents and robots. In this talk I will describe each of these theoretical perspectives, discuss their similarities and differences, and their relevance for the three core areas of affective computing. I will focus in particular on contrasting the dimensional and the componential perspectives, both of which use a set of underlying dimensions, or variables, to represent distinct affective states. I will discuss the implications of using the different perspectives as the theoretical foundations for emotion recognition, emotion modeling and emotion expression, emphasizing the scope of processes supported by each perspective and differences in data availability.

10.10-10.30 Coffee break

10.30-11.50 Session 1: From emotional dimensions to automatic analysis (Chair: James Crowley, INRIA)
11.50-13.20 Lunch

13.20-14.00 Keynote 2 (Chair: Maja Pantic, Imperial College London)
A journey through measurements of the arousal dimension

We often think of the two main dimensions of emotion as "arousal" and "valence". While we don't have a perfect measure of either, the skin, we are told, is innervated mainly by the sympathetic nervous system, and its changes in conductance can serve as one possible measure of the arousal dimension. Recently, my team and I have been learning a lot about measuring arousal 24/7 using skin conductance. This talk will touch on some findings related to autonomic arousal in daytime activity, autism, epilepsy, pain, stress, sensory processing disorders, PTSD, and sleep. I'll tell stories from these latest explorations and raise some research challenges.

14.00-15.20 Session 2: Audio-based affect analysis (Chair: Björn Schuller, TUM)
15.20-15.40 Coffee break

15.40-17.00 Session 3: Vision-based expression analysis (Chair: Hatice Gunes, Imperial College London)
  • 15.40-16.00 Expression of Emotional States during Locomotion based on Canonical Parameters
    Martin Inderbitzin, Aleksander Väljamäe, Jose Maria Blanco Calvo, Paul F.M.J. Verschure and Ulysses Bernardet (University of Pompeu Fabra / Catalan Institute of Research and Advanced Studies)
  • 16.00-16.20 A SSIM-Based Approach for Finding Similar Facial Expressions
    Abhinav Dhall, Akshay Asthana and Roland Goecke (Australian National University / University of Canberra)
  • 16.20-16.40 Individual Identification Based on Facial Dynamics during Expressions Using Active-Appearance-based Hidden Markov Models
    Adam Gaweda and Eric Patterson (University of North Carolina Wilmington)
  • 16.40-17.00 Analysis and Synthesis of Facial Expressions Using Decomposable Nonlinear Generative Models
    Chan-Su Lee and Dimitris Samaras (Yeungnam University / Stony Brook University)

17.00-17.20 Coffee break

17.20-18.10 Session 4: Outlook and Discussion (Chair: Maja Pantic, Imperial College London)
  • 17.20-17.40 Emotion Representation, Analysis and Synthesis in Continuous Space: A Survey
    Hatice Gunes, Bjoern Schuller, Maja Pantic and Roddy Cowie (Imperial College London / Technische Universität München / Queen's University Belfast)
  • 17.40-18.10 Panel discussion
    Panelists: Jeffrey Cohn (Univ. of Pittsburgh), Hatice Gunes (Imperial College London), Christian Kaernbach (Univ. Kiel), Rosalind Picard (MIT), Karl Ricanek (UNCW), Börn Schuller (TUM), Marian Stewart Bartlett (UCSD)

Submission Policy:

In submitting a manuscript to this workshop, the authors acknowledge that no paper substantially similar in content has been submitted to another conference or workshop.
Manuscripts should be in the IEEE FG paper format.
Authors should submit papers as a PDF file.
Papers accepted for the workshop will be allocated 6 pages in the proceedings, with the option of having up to 2 extra pages.
EmoSPACE reviewing is double blind. Reviewing will be by members of the program committee. Each paper will receive at least two reviews. Acceptance will be based on relevance to the workshop, novelty, and technical quality.
Submission and reviewing will be handled via the Microsoft CMT system.

Please submit your paper at
Document Actions
Powered by Plone

Portal usage statistics