AVEC 2018

Seoul, Korea

AVEC 2018

The Audio/Visual Emotion Challenge and Workshop (AVEC 2018) “Bipolar Disorder and Cross-cultural Affect” is a satellite event of ACM MM 2018 and the eighth competition aimed at comparison of multimedia processing and machine learning methods for automatic audio, visual, and audio-visual health and emotion sensing, with all participants competing under strictly the same conditions.

Deadline: 08 July 2018

AVEC 2018 is an ACM MM Challenge Workshop themed around two topics: for the first time in a challenge bipolar disorder and emotion recognition. Bipolar disorder (BD) is a serious mental health disorder, with patients experiencing either manic or depressive episodes. Those with BD tend to live with this long-term. The purpose of the Audio/Visual Emotion Challenge and Workshop (AVEC) series is to bring together multiple communities from different disciplines, in particular the audio-visual multimedia communities and those in the psychological and social sciences who study expressive behaviour and emotion. One of the goals of AVEC is to compare the relative merits of different modalities (e.g., audio and video) under well-defined and strictly comparable conditions and establish to what extent fusion of the approaches is possible and beneficial. A second motivation is the need to advance health and emotion recognition systems to be able to deal with fully naturalistic behaviour in large volumes of un-segmented, non-prototypical and non-preselected data as this is exactly the type of data that new generation of affect-oriented multimedia and human-machine/human-robot communication interfaces have to face in the real world.

Call for papers

We are calling for participation in the 8th Audio/Visual Emotion Challenge and Workshop (AVEC 2018), an ACM MM Challenge Workshop themed around two topics: for the first time in a challenge bipolar disorder and emotion recognition. Bipolar disorder (BD) is a serious mental health disorder, with patients experiencing either manic or depressive episodes. Those with BD tend to live with this long-term. The purpose of the Audio/Visual Emotion Challenge and Workshop (AVEC) series is to bring together multiple communities from different disciplines, in particular the audio-visual multimedia communities and those in the psychological and social sciences who study expressive behaviour and emotion. The AVEC 2018 challenge theme is on Bipolar disorder and Cross-cultural emotion, and it is the eighth competition event aimed at comparison of multimedia processing and machine learning methods for automatic audio, visual, and audiovisual health and emotion analysis, with all participants competing under strictly the same conditions. It introduces major novelties this year with three separated sub-challenges:

  • Bipolar Disorder Sub-challenge (BDS) — participants have to classify patients suffering from bipolar disorder into remission, hypo-mania and mania, as defined by the young mania rating scale, from audio-visual recordings of structured interviews (BD corpus); performance is measured by the unweighted average recall over the three classes.
  • Cross-cultural Emotion Sub-challenge (CES) — participants have to predict the level of three emotional dimensions (arousal, valence, and likability) time-continuously in a cross-cultural setup (German => Hungarian) from audio-visual recordings of dyadic interactions (SEWA corpus); performance is the concordance correlation coefficient (CCC) averaged over the dimensions.
  • Gold-standard Emotion Sub-Challenge (GES) — participants have to generate a gold-standard (i.e., a single time series of emotion labels) from individual ratings of emotional dimensions (arousal, valence) that will be evaluated by a multimodal (audio, video, physiology) emotion recognition system from recordings of dyadic interactions (RECOLA corpus); performance is the concordance correlation coefficient (CCC) averaged over the dimensions.

In order to participate in the Challenge, please register your team by following the challenge guidelines.

Topics of interest

We encourage both - contributions aiming at highest performance w.r.t. the baselines provided by the organisers, and contributions aiming at finding new and interesting insights w.r.t. these challenges. Besides participation in the challenge, we are also encouraging submissions of original contributions on the following topics (not limited to):

  • Multimodal Affect Sensing
    • Audio-based Health/Emotion Recognition
    • Video-based Health/Emotion Recognition
    • Physiological-based Health/Emotion Recognition
    • Multimodal Representation Learning
    • Semi-supervised and Unsupervised Learning
    • Multi-view learning of Multiple Dimensions
    • Personalised Health/Emotion Recognition
    • Context in Health/Emotion Recognition
    • Multiple Rater Ambiguity and Asynchrony
  •  Application
    • Multimedia Coding and Retrieval
    • Mobile and Online Applications

Dates

Paper submission: June 30, 2018
Notification of acceptance: July 31, 2018
Camera ready paper: August 14, 2018
Workshop: October 22-26, 2018 (to be communicated)

Submissions

See https://sites.google.com/view/avec2018/home/submission-policy for the submission policy.

Organizers

Fabien Ringeval, Université Grenoble Alpes, CNRS, France
Björn Schuller, Imperial College London/University of Augsburg, UK/Germany
Michel Valstar, University of Nottingham, UK
Roddy Cowie, Queen’s University Belfast, UK
Maja Pantic, Imperial College London/University of Twente, UK/The Netherlands