arXiv 2305.033692023-05-05cs.LGcs.AIcs.CLcs.MM

MuSe 2023多模态情感分析挑战赛：模仿情绪、跨文化幽默与个性化

The MuSe 2023 Multimodal Sentiment Analysis Challenge: Mimicked Emotions, Cross-Cultural Humour, and Personalisation

University of Augsburg（奥格斯堡大学）；Hume AI（休谟人工智能公司）；University of Passau（帕绍大学）；University of Ulm（乌尔姆大学）；Nanyang Technological University（南洋理工大学）；Imperial College London（帝国理工学院）

Lukas Christ, Shahin Amiriparian, Alice Baird, Alexander Kathan, Niklas Müller, Steffen Klug, Chris Gagne, Panagiotis Tzirakis, Eva-Maria Meßner, Andreas König,… 展开作者

Lukas Christ, Shahin Amiriparian, Alice Baird, Alexander Kathan, Niklas Müller, Steffen Klug, Chris Gagne, Panagiotis Tzirakis, Eva-Maria Meßner, Andreas König, Alan Cowen, Erik Cambria, Björn W. Schuller

备注：: Baseline paper for the 4th Multimodal Sentiment Analysis Challenge (MuSe) 2023, a workshop at ACM Multimedia 2023

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文介绍MuSe 2023多模态情感分析挑战赛的三类子任务、对应数据集与特征集，并给出基于GRU-RNN的基线系统在各任务上的性能结果。

摘要：

MuSe 2023是一组针对三类当前主流多模态情感与情绪分析问题的共享任务：在模仿情绪子挑战赛（MuSe-Mimic）中，参赛者需预测三个连续情绪目标。该子挑战赛使用由用户生成视频组成的Hume-Vidmimic数据集。跨文化幽默检测子挑战赛（MuSe-Humour）提供了帕绍自发足球教练幽默（Passau Spontaneous Football Coach Humour, Passau-SFCH）数据集的扩展版本，参赛者需预测跨文化场景下自发幽默的存在情况。个性化子挑战赛（MuSe-Personalisation）基于乌尔姆-特里尔社会压力测试（Ulm-Trier Social Stress Test, Ulm-TSST）数据集，包含受试者在压力情境下的记录，该任务需预测唤醒度和效价信号，同时会提供部分测试标签以支持个性化建模。MuSe 2023旨在汇聚来自音视频情绪识别、自然语言处理、信号处理、健康信息学等不同研究领域的广泛参与者。在这篇基线论文中，我们介绍了相关数据集、子挑战赛及提供的特征集。我们采用门控循环单元（Gated Recurrent Unit, GRU）-循环神经网络（Recurrent Neural Network, RNN）作为有竞争力的基线系统，在各子挑战赛的测试集上，其在MuSe-Mimic任务中（三个连续强度目标的平均）皮尔逊相关系数为0.4727，在MuSe-Humour任务中曲线下面积（Area Under the Curve, AUC）为0.8310，在MuSe-Personalisation子挑战赛中唤醒度的一致性相关系数（Concordance Correlation Coefficient, CCC）为0.7482、效价的CCC为0.7827。

英文摘要：

The MuSe 2023 is a set of shared tasks addressing three different contemporary multimodal affect and sentiment analysis problems: In the Mimicked Emotions Sub-Challenge (MuSe-Mimic), participants predict three continuous emotion targets. This sub-challenge utilises the Hume-Vidmimic dataset comprising of user-generated videos. For the Cross-Cultural Humour Detection Sub-Challenge (MuSe-Humour), an extension of the Passau Spontaneous Football Coach Humour (Passau-SFCH) dataset is provided. Participants predict the presence of spontaneous humour in a cross-cultural setting. The Personalisation Sub-Challenge (MuSe-Personalisation) is based on the Ulm-Trier Social Stress Test (Ulm-TSST) dataset, featuring recordings of subjects in a stressed situation. Here, arousal and valence signals are to be predicted, whereas parts of the test labels are made available in order to facilitate personalisation. MuSe 2023 seeks to bring together a broad audience from different research communities such as audio-visual emotion recognition, natural language processing, signal processing, and health informatics. In this baseline paper, we introduce the datasets, sub-challenges, and provided feature sets. As a competitive baseline system, a Gated Recurrent Unit (GRU)-Recurrent Neural Network (RNN) is employed. On the respective sub-challenges' test datasets, it achieves a mean (across three continuous intensity targets) Pearson's Correlation Coefficient of .4727 for MuSe-Mimic, an Area Under the Curve (AUC) value of .8310 for MuSe-Humor and Concordance Correlation Coefficient (CCC) values of .7482 for arousal and .7827 for valence in the MuSe-Personalisation sub-challenge.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。