A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition

<p dir="ltr">Adult facial expression recognition (FER) is essential for human-computer interaction, mental health assessment, and social robotics applications because it improves user experiences and emotional well-being. This study presents a novel attention mechanism-based transfor...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Uzma Nawaz (21980708) (author)
مؤلفون آخرون: Zubair Saeed (19325647) (author), Kamran Atif (22457845) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513534679842816
author Uzma Nawaz (21980708)
author2 Zubair Saeed (19325647)
Kamran Atif (22457845)
author2_role author
author
author_facet Uzma Nawaz (21980708)
Zubair Saeed (19325647)
Kamran Atif (22457845)
author_role author
dc.creator.none.fl_str_mv Uzma Nawaz (21980708)
Zubair Saeed (19325647)
Kamran Atif (22457845)
dc.date.none.fl_str_mv 2025-04-04T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2025.3555510
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Novel_Transformer-Based_Approach_for_Adult_s_Facial_Emotion_Recognition/30393349
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Facial emotion recognition
transformers
deep learning
FER2013
CK+
AffectNet
AFEW
RAF-DB
emotion recognition
Accuracy
Brain modeling
Real-time systems
Adaptation models
Lighting
Human computer interaction
Facial features
dc.title.none.fl_str_mv A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Adult facial expression recognition (FER) is essential for human-computer interaction, mental health assessment, and social robotics applications because it improves user experiences and emotional well-being. This study presents a novel attention mechanism-based transformer approach designed to capture detailed patterns in facial features and dynamically focus on the most relevant regions for enhanced accuracy. Unlike conventional deep learning approaches, our method integrates an adaptive attention mechanism and dynamic token pruning, which optimizes computational efficiency while maintaining high accuracy. The model is evaluated on five widely used datasets: FER2013, CK+, AffectNet, RAF-DB, and AFEW. It achieves state-of-the-art performance, with accuracies of 98.67% on FER2013, 99.52% on CK+, 99.3% on AffectNet, 96.3% on AFEW, and 98.45% on RAF-DB. An ablation study further validates the contribution of each model component, and comparisons with CNN-based and transformer-based approaches confirm the effectiveness of the model. These findings establish the proposed method as a significant advancement in FER, which offers a scalable and efficient solution for real-world applications.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3555510" target="_blank">https://dx.doi.org/10.1109/access.2025.3555510</a></p>
eu_rights_str_mv openAccess
id Manara2_361ba832583d29a64c5f08416c7f141e
identifier_str_mv 10.1109/access.2025.3555510
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30393349
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Novel Transformer-Based Approach for Adult’s Facial Emotion RecognitionUzma Nawaz (21980708)Zubair Saeed (19325647)Kamran Atif (22457845)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationMachine learningFacial emotion recognitiontransformersdeep learningFER2013CK+AffectNetAFEWRAF-DBemotion recognitionAccuracyBrain modelingReal-time systemsAdaptation modelsLightingHuman computer interactionFacial features<p dir="ltr">Adult facial expression recognition (FER) is essential for human-computer interaction, mental health assessment, and social robotics applications because it improves user experiences and emotional well-being. This study presents a novel attention mechanism-based transformer approach designed to capture detailed patterns in facial features and dynamically focus on the most relevant regions for enhanced accuracy. Unlike conventional deep learning approaches, our method integrates an adaptive attention mechanism and dynamic token pruning, which optimizes computational efficiency while maintaining high accuracy. The model is evaluated on five widely used datasets: FER2013, CK+, AffectNet, RAF-DB, and AFEW. It achieves state-of-the-art performance, with accuracies of 98.67% on FER2013, 99.52% on CK+, 99.3% on AffectNet, 96.3% on AFEW, and 98.45% on RAF-DB. An ablation study further validates the contribution of each model component, and comparisons with CNN-based and transformer-based approaches confirm the effectiveness of the model. These findings establish the proposed method as a significant advancement in FER, which offers a scalable and efficient solution for real-world applications.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3555510" target="_blank">https://dx.doi.org/10.1109/access.2025.3555510</a></p>2025-04-04T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3555510https://figshare.com/articles/journal_contribution/A_Novel_Transformer-Based_Approach_for_Adult_s_Facial_Emotion_Recognition/30393349CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/303933492025-04-04T06:00:00Z
spellingShingle A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
Uzma Nawaz (21980708)
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Facial emotion recognition
transformers
deep learning
FER2013
CK+
AffectNet
AFEW
RAF-DB
emotion recognition
Accuracy
Brain modeling
Real-time systems
Adaptation models
Lighting
Human computer interaction
Facial features
status_str publishedVersion
title A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_full A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_fullStr A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_full_unstemmed A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_short A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_sort A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
topic Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Machine learning
Facial emotion recognition
transformers
deep learning
FER2013
CK+
AffectNet
AFEW
RAF-DB
emotion recognition
Accuracy
Brain modeling
Real-time systems
Adaptation models
Lighting
Human computer interaction
Facial features