Summary of The Muse 2024 Multimodal Sentiment Analysis Challenge: Social Perception and Humor Recognition, by Shahin Amiriparian et al.
The MuSe 2024 Multimodal Sentiment Analysis Challenge: Social Perception and Humor Recognition
by Shahin Amiriparian, Lukas Christ, Alexander Kathan, Maurice Gerczuk, Niklas Müller, Steffen Klug, Lukas Stappen, Andreas König, Erik Cambria, Björn Schuller, Simone Eulitz
First submitted to arxiv on: 11 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces the Multimodal Sentiment Analysis Challenge (MuSe) 2024, a research initiative that aims to advance our understanding and application of sentiment analysis and affective computing across multiple modalities. The challenge comprises two sub-challenges: Social Perception Sub-Challenge (MuSe-Perception), which focuses on predicting social attributes from audio-visual data, and Cross-Cultural Humor Detection Sub-Challenge (MuSe-Humor), which targets the detection of spontaneous humor in a cross-lingual and cross-cultural setting. The paper provides details on each sub-challenge, its corresponding dataset, extracted features, and discusses challenge baselines. To tackle these challenges, the authors propose using Transformers and expert-designed features, training Gated Recurrent Unit (GRU)-Recurrent Neural Network (RNN) models on them. This baseline system achieves a mean Pearson’s Correlation Coefficient (ρ) of 0.3573 for MuSe-Perception and an Area Under the Curve (AUC) value of 0.8682 for MuSe-Humor. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The Multimodal Sentiment Analysis Challenge (MuSe) is a research project that aims to understand and analyze sentiment in different ways, using many types of data like audio and video. The challenge has two parts: one part looks at how people are perceived socially based on what they say and do, and the other part tries to detect humor in videos from different cultures. The goal of MuSe is to bring together experts from different fields to work together and share their knowledge. This paper tells us about each part of the challenge, including the data used, features extracted, and how well a baseline system did on these tasks. |
Keywords
» Artificial intelligence » Auc » Neural network » Rnn
