The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements

Stappen, Lukas; Baird, Alice; Schumann, Lea; Björn, Schuller

doi:10.1109/taffc.2021.3097002

Cited by 39 publications

(18 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When predicting arousal, the models tend to overfit, while underfitting can be observed for the prediction of valence. This was also found in [24,43,47] and is possibly due to the chosen data split, which is speaker-independent, hence leading to imbalances in the label distribution [44]. For arousal, the results without normalisation are slightly stronger on the development set.…”

Section: Continuous Emotion Fusionmentioning

confidence: 59%

“…By doing so, we used them to train models for dimensional affect recognition. To this end, we utilise the MuSe-CaR database [44], used in the 2020 and 2021 Multimodal Sentiment Analysis real-life media Emotion Challenges (MuSe) [41,43], and several other works [13,24,40,42,45,47].…”

Section: Methodsmentioning

confidence: 99%

“…Each 250 ms of the video dataset is labelled by at least five annotators, which are used for the following experiments. For more information, we refer the interested reader to the challenge [41] and database paper [44].…”

Section: Continuous Emotion Fusionmentioning

confidence: 99%

See 2 more Smart Citations

MuSe-Toolbox: The Multimodal Sentiment Analysis Continuous Annotation Fusion and Discrete Class Transformation Toolbox

Stappen

Schumann

Sertolli

et al. 2021

Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge

Self Cite

View full text Add to dashboard Cite

We introduce the MuSe-Toolbox -a Python-based open-source toolkit for creating a variety of continuous and discrete emotion gold standards. In a single framework, we unify a wide range of fusion methods and propose the novel Rater Aligned Annotation Weighting (RAAW ), which aligns the annotations in a translationinvariant way before weighting and fusing them based on the interrater agreements between the annotations. Furthermore, discrete categories tend to be easier for humans to interpret than continuous signals. With this in mind, the MuSe-Toolbox provides the functionality to run exhaustive searches for meaningful class clusters in the continuous gold standards. To our knowledge, this is the first toolkit that provides a wide selection of state-of-the-art emotional gold standard methods and their transformation to discrete classes. Experimental results indicate that MuSe-Toolbox can provide promising and novel class formations which can be better predicted than hard-coded classes boundaries with minimal human intervention. The implementation 1 is out-of-the-box available with all dependencies using a Docker container 2 . CCS CONCEPTS• Information systems → Multimedia and multimodal retrieval; • Computing methodologies → Artificial intelligence.

show abstract

Section: Continuous Emotion Fusionmentioning

confidence: 59%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MuSe-Toolbox: The Multimodal Sentiment Analysis Continuous Annotation Fusion and Discrete Class Transformation Toolbox

Stappen

Schumann

Sertolli

et al. 2021

Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge

Self Cite

View full text Add to dashboard Cite

show abstract

“…In total, 26 distinct combinations were identified using data of six different modalities. [188], [262], [265], [273], [274], [277], [294], [300], [376], [379], [393], Video & Audio & Sensor [252], [296], [409], Video & Audio [153], [171], [229], [253], [255], [266], [275], [281], [287], [292], [295], [298], [315], Video & Text [199], Video & Sensor [271], Video & Signal [250], [283], Image & Audio & Text [111], [175], [204], [213], [216], [263], [264], [288], [340], [396], [406], Image & Audio & Sensor & Signal [366], Image & Audio & Sensor [249], [334], [335], Image & Audio …”

Section: B Taskmentioning

confidence: 99%

A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions

2023

View full text Add to dashboard Cite

Multimodal machine learning (MML) is a tempting multidisciplinary research area where heterogeneous data from multiple modalities and machine learning (ML) are combined to solve critical problems. Usually, research works use data from a single modality, such as images, audio, text, and signals. However, real-world issues have become critical now, and handling them using multiple modalities of data instead of a single modality can significantly impact finding solutions. ML algorithms play an essential role by tuning parameters in developing MML models. This paper reviews recent advancements in the challenges of MML, namely: representation, translation, alignment, fusion and co-learning, and presents the gaps and challenges. A systematic literature review (SLR) applied to define the progress and trends on those challenges in the MML domain. In total, 1032 articles were examined in this review to extract features like source, domain, application, modality, etc. This research article will help researchers understand the constant state of MML and navigate the selection of future research directions.

show abstract

“…In this section, we describe the dataset and the prediction task environment. The MuSe-CaR dataset 29 is a large, multimodal dataset focused on sentiment modeling in automotive video reviews supporting various research directions with predefined data subsets holding unique, task-specific properties and labels. In this article, we utilize the MuSe-Topic subset.…”

Section: Dataset: the Muse-topic Subchallengementioning

confidence: 99%

Sentiment Analysis and Topic Recognition in Video Transcriptions

et al. 2021

View full text Add to dashboard Cite

The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements

Cited by 39 publications

References 76 publications

MuSe-Toolbox: The Multimodal Sentiment Analysis Continuous Annotation Fusion and Discrete Class Transformation Toolbox

MuSe-Toolbox: The Multimodal Sentiment Analysis Continuous Annotation Fusion and Discrete Class Transformation Toolbox

A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps and Future Directions

Sentiment Analysis and Topic Recognition in Video Transcriptions

Contact Info

Product

Resources

About