Paper Submission

A full day workshop in conjunction with ACM Multimedia 2022

Paper submission (all participants): Please be reminded that a paper submission and at least one upload on the test set are mandatory for participation in the Challenge. However, paper contributions within the scope (below) are also welcome if the authors do not intend to participate in the Challenge itself. In any case, please submit your paper until 08 July 2022.

Manuscripts must follow the ACM MM 2022 paper format, for details see the ACM CfP. Authors should submit papers as PDF file.

Submission will be via CMT:

The introductory paper on the Challenge provides extensive descriptions and baseline results. All participants are asked to avoid too extensive descriptions of the challenge, data, or the already provided features in their submissions – short descriptions of e.g., the database(s), however, are often appropriate. All papers must include the following citation:

In BibTeX, the reference is:


title={The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress},

author={Christ, Lukas and Amiriparian, Shahin and Baird, Alice and Tzirakis, Panagiotis and Kathan, Alexander and Müller, Niklas and Stappen, Lukas and Meßner, Eva-Maria and König, Andreas and Cowen, Alan and Cambria, Erik and Schuller, Bj\"orn W. },

booktitle={Proceedings of the 3rd Multimodal Sentiment Analysis Challenge},


address = {Lisbon, Portugal},

publisher = {Association for Computing Machinery},

note = {Workshop held at ACM Multimedia 2022, to appear}


Please note:

  • The submission deadline is at 11:59 p.m. of the stated deadline date Anywhere on Earth.

  • Papers accepted for the workshop will be allocated 5-8 pages (plus at most 2 additional pages for the references) in the proceedings and have to be presented.

  • Participants may contribute to all Sub-Challenges at a time. A training and development partitioning will allow for tests and results to be reported by the participants apart from their results on the official test set. Papers may well report additional results on other databases.

  • Papers need to cite the baseline paper (cf. above).

  • Each paper will receive at least three reviews. Acceptance will be based on relevance to the workshop, novelty, and technical quality.

  • In your initial paper submission, you do not need to include the information on your rank on the leaderboard. You can add this information later in the camera-ready version.

Other Contributions

A core discipline of multimedia research is to handle big data and develop effective embedding and fusing strategies in order to combine multiple modalities and understand multimedia content better. The recordings in the databases of MuSe 2022 contain different modalities: video in the form of domain-context, perceived gestures and facial expressions; audio through voice prosody and intonations as well as domain-dependent environment sounds; and text via natural spoken language.

We encourage 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. to the topic of these challenges, especially:

Multimodal Affect/ Emotion/ Sentiment Sensing

        • Audio-based Emotion Recognition

        • Video-based Emotion Recognition

        • Text-based Sentiment/ Emotion Recognition

        • Multimodal Representation Learning

        • Transfer Learning

        • Semi-supervised and Unsupervised Learning

        • Multi-view learning of Multiple Dimensions

        • Aspect Extraction

        • Context in Emotion Recognition


        • Multimedia Coding and Retrieval

        • Mobile and Online Applications