MuSe 2022
The Multimodal Sentiment Analysis Challenge
Humor, Emotional Reactions, and Stress
We are pleased to announce MuSe 2022!
Challenge: This year's Multimodal Sentiment Analysis Challenge (MuSe 2022) focuses on multimodal sentiment analysis, emotion recognition and humor detection utilising three different data sets. The competition is a satellite event of the 30th ACM International Conference on Multimedia (Lisbon, Portugal), aimed to compare multimedia processing and deep learning methods for audiovisual, biological, and textual based sentiment and emotion sensing, under a common experimental condition set.
The goal of the MuSe is to provide a common benchmark test set for multimodal information processing and to bring together the Affective Computing, Sentiment Analysis, and Health Informatics research communities, to compare the merits of multimodal fusion for a large amount of modalities under well-defined conditions.
MuSe 2022 features three sub-challenges based on three datasets:
Humor Detection Sub-Challenge (MuSe-Humor): Detecting the presence of humor in football press conference recordings. The sub-challenge is based on the novel Passau Spontaneous Football Coach Humor (Passau-SFCH) dataset.
Emotional Reactions Sub-Challenge: Predicting the intensities of seven self-reported emotions (Adoration, Amusement, Anxiety, Disgust, Empathic Pain, Fear, Surprise) from user-generated reactions to emotionally evocative videos. The sub-challenge is based on the novel Hume-Reaction data set
Multimodal Emotional Stress Sub-challenge (MuSe-Stress): Predicting the level of valence and psycho-physiological arousal in a time-continuous manner from audio-visual recordings. This sub-challenge is a modified version of last year's MuSe-Stress challenge, based on the Ulm-TSST featuring people in a stressed disposition.
Important Dates (preliminary):
11th April: Data, baseline paper & code available
11th April: Registration opens
8th June: Evaluation System opens
8th July: Paper due
29th July: Paper notification
7th August: Camera-ready paper due
October 10-14, exact day tba: Full-day workshop at ACM MM 2022, Lisbon, Portugal