Facial Expression Recognition in the Wild with Application in Robotics

Han, Hasan; Karadeniz, Oguzcan; Sönmez, Elena Battini; Dalyan, Tuğba; Sarioğlu, Baykal

doi:10.1109/ubmk52708.2021.9558909

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other initiatives combine the imitative aspect with identification, whereby emotions in individuals are identified and the machine imitates others in response to enhance interaction (Gaeta et al, 2023;Han et al, 2023). The interaction of these imitative models with students can be carried out in various ways, such as through empathetic agents that can even be integrated into virtual reality systems (Hernández and Ramírez, 2016).…”

Section: Introductionmentioning

confidence: 99%

Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence

Roda-Segarra,

Mengual-Andrés,

Payà Rico

2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Research in the field of Artificial Intelligence applied to emotions in the educational context has experienced significant growth in recent years. However, despite the field’s profound implications for the educational community, the social impact of this scientific production on digital social media remains unclear. To address this question, the present research has been proposed, aiming to analyze the social impact of scientific production on the use of Artificial Intelligence for emotions in the educational context. For this purpose, a sample of 243 scientific publications indexed in Scopus and Web of Science has been selected, from which a second sample of 6,094 social impact records has been extracted from Altmetric, Crossref, and PlumX databases. A dual analysis has been conducted using specially designed software: on one hand, the scientific sample has been analyzed from a bibliometric perspective, and on the other hand, the social impact records have been studied. Comparative analysis based on the two dimensions, scientific and social, has focused on the evolution of scientific production with its corresponding social impact, sources, impact, and content analysis. The results indicate that scientific publications have had a high social impact (with an average of 25.08 social impact records per publication), with a significant increase in research interest starting from 2019, likely driven by the emotional implications of measures taken to curb the COVID-19 pandemic. Furthermore, a lack of alignment has been identified between articles with the highest scientific impact and those with the highest social impact, as well as a lack of alignment in the most commonly used terms from both scientific and social perspectives, a significant variability in the lag in months for scientific research to make an impact on social media, and the fact that the social impact of the research did not emerge from the interest of Twitter users unaffiliated with the research, but rather from the authors, publishers, or scientific institutions. The proposed comparative methodology can be applied to any field of study, making it a useful tool given that current trends in accreditation agencies propose the analysis of the repercussion of scientific research in social media.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence

Roda-Segarra,

Mengual-Andrés,

Payà Rico

2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…The authors highlight the comparative performance of their model compared to state-of-the-art methods applied on popular datasets like JAFFE and CK+ and also the significance of heterogeneous datasets when collected by the humanoid NAO robot for robust recognition. [8] present a study using a mobile robot platform and achieved good performance with an ensemble method for "in-the-wild" images. However, it is a small-scale study because the authors used only 60 images for testing.…”

Section: Introductionmentioning

confidence: 99%

I am Only Happy When There is Light: The Impact of Environmental Changes on Affective Facial Expressions Recognition

Jirak¹,

Sciutti²,

Barros³

2022

Preprint

View full text Add to dashboard Cite

Human-robot interaction (HRI) benefits greatly from advances in the machine learning field as it allows researchers to employ high-performance models for perceptual tasks like detection and recognition. Especially deep learning models, either pre-trained for feature extraction or used for classification, are now established methods to characterize human behaviors in HRI scenarios and to have social robots that understand better those behaviors. As HRI experiments are usually small-scale and constrained to particular lab environments, the questions are how well can deep learning models generalize to specific interaction scenarios, and further, how good is their robustness towards environmental changes? These questions are important to address if the HRI field wishes to put social robotic companions into real environments acting consistently, i.e. changing lighting conditions or moving people should still produce the same recognition results. In this paper, we study the impact of different image conditions on the recognition of arousal and valence from human facial expressions using the FaceChannel framework [1]. Our results show how the interpretation of human affective states can differ greatly in either the positive or negative direction even when changing only slightly the image properties. We conclude the paper with important points to consider when employing deep learning models to ensure sound interpretation of HRI experiments.

show abstract

Facial Expression Recognition on Wild and Multi-Label Faces with Deep Learning

Han,

Sönmez

2023

2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)

View full text Add to dashboard Cite

Facial Expression Recognition in the Wild with Application in Robotics

Cited by 4 publications

References 25 publications

Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence

Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence

I am Only Happy When There is Light: The Impact of Environmental Changes on Affective Facial Expressions Recognition

Facial Expression Recognition on Wild and Multi-Label Faces with Deep Learning

Contact Info

Product

Resources

About