Uncertainties of facial emotion recognition technologies and the automation of emotional labour

Bjørnsten, Thomas; Sørensen, Mette-Marie Zacher

doi:10.1080/14626268.2017.1383271

Cited by 6 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Veit et al(2017) used a multi-task network to jointly learn to clean up noisy annotations and classify image. For the FER task, Bjørnsten and Zacher Sørensen (2017) analyzed that the uncertainty in face image processing is caused by issues such as temporality and static images. Wu et al (2018) proposed a variant of maxout activation called Max-Feature-Map (MFM).…”

Section: Research On Uncertainty In Facial Expression Recognitionmentioning

confidence: 99%

An Optimization Algorithm for the Uncertainties of Classroom Expression Recognition Based on SCN

Niu

Zhou

et al. 2022

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

With the gradual application of facial expression recognition (FER) technology in various fields, the facial expression datasets based on specific scenes have gradually increased, effectively improving the application effect. However, the facial images of students collected in real classroom scenes often have problems, such as front and rear occlusion, blurred images, and small targets. Moreover, the current students' classroom expression recognition technology faces several challenges as a result of sample uncertainties. Therefore, this paper proposes an optimization algorithm for the uncertainties based on SCN. The correction weight of the sample through the sample weight was calculated, and the loss function was designed according to the correction weight. The dynamic threshold is obtained by combining the threshold in the noise relabeling module and the correction weight. The experimental results on public datasets and self-built classroom expression dataset show that the optimization algorithm effectively improves the robustness of SCN to uncertain samples.

show abstract

Section: Research On Uncertainty In Facial Expression Recognitionmentioning

confidence: 99%

An Optimization Algorithm for the Uncertainties of Classroom Expression Recognition Based on SCN

Niu

Zhou

et al. 2022

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Yet developers, or at least the marketers of their products, appear confident that using machine vision algorithms to analyse facial expressions can tell us that somebody is 99% angry and 0.5% sad, for instance. In this case, the facial expressions are proxies that are presumed to correlate perfectly with a person's emotions, although this assumption builds upon psychological theories that were arguably outdated decades ago (Bjørnsten & Zacher Sørensen, 2017). We measure what we can measure and make claims based on that.…”

Section: Correlation Is Easier Than Causationmentioning

confidence: 99%

Data visualization in society

McBride

2021

Journal of the Australian Library and Information Association

View full text Add to dashboard Cite

for a stimulating and productive three-year collaboration. They are all authors of chapters in this book. We are grateful to all of the authors who have contributed to this collection, for their excellent contributions, their receptiveness to feedback and their patience during the long process of bringing the book to fruition. We are extremely grateful to the University of Agder for hosting the INDVIL project and for the administrative support provided to us. In June 2018 we held a seminar with many of the book's authors at the Metochi Study Centre on the island of Lesbos. We thank the staff at Metochi for the wonderful service they provided and the fantastic atmosphere which enabled us to work hard together on the book. We thank reviewers for taking the time to read our many chapters with care and for providing helpful feedback. We are grateful also to Alberto Cairo for his extremely generous foreword, and to esteemed data visualization scholars for endorsing this volume on its cover. We want to express our enormous gratitude to all of the brilliant data visualizers whose work inspires our own, especially Andy Kirk, for ongoing support and openness to dialogue. We could not have made it through the final stages of producing this book without the invaluable help of Robin Steedman, whose work as an editorial assistant has been faultless. Thank you Robin. We also thank Prisca Schmarsow of Eyedea Studio (https://eyedeastudio.london/) for lovely cover design and the staff at the Amsterdam University Press for their assistance along the way. Finally, Helen would like to thank Martin, and Martin would like to thank Helen, for the enjoyable and rewarding experience of editing this book together.

show abstract

“…Yet developers, or at least the marketers of their products, appear con dent that using machine vision algorithms to analyse facial expressions can tell us that somebody is 99% angry and 0.5% sad, for instance. In this case, the facial expressions are proxies that are presumed to correlate perfectly with a person's emotions, although this assumption builds upon psychological theories that were arguably outdated decades ago (Bjørnsten & Zacher Sørensen, 2017). We measure what we can measure and make claims based on that.…”

Section: Correlation Is Easier Than Causationmentioning

confidence: 99%

Ways of knowing with data visualizations

Rettberg¹

2020

Data Visualization in Society

View full text Add to dashboard Cite

Data visualizations combine numeric data with visual representation, and these modes allow them to express certain kinds of knowledge more easily than others. This chapter uses examples of historical data visualizations in order to examine what ways of knowing they privilege. What is the di ference between the spatial organization of tools in prehistoric homes and a photograph or bar chart showing information about the same tools, in terms of the kinds of knowledge they enable? How do the systems for gathering and visualizing data during the 18 th and 19 th centuries shape our understanding of the world? How do data visualizations make us feel that they are objective? How do they shape our ideas of what is possible?

show abstract

Uncertainties of facial emotion recognition technologies and the automation of emotional labour

Cited by 6 publications

References 13 publications

An Optimization Algorithm for the Uncertainties of Classroom Expression Recognition Based on SCN

An Optimization Algorithm for the Uncertainties of Classroom Expression Recognition Based on SCN

Data visualization in society

Ways of knowing with data visualizations

Contact Info

Product

Resources

About