Physiological inspired neural networks for emotion recognition

Detalhes bibliográficos
Autor(a) principal: Ferreira, Pedro M.
Data de Publicação: 2018
Outros Autores: Marques, Filipe, Cardoso, Jaime S., Rebelo, Ana
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/11328/2469
https://doi.org/10.1109/ACCESS.2018.2870063
Resumo: Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.
id RCAP_6a71fe72de4a43e9bc30252458fb677e
oai_identifier_str oai:repositorio.upt.pt:11328/2469
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Physiological inspired neural networks for emotion recognitionFacial expressions recognitionConvolutional neural networksRegularizationDomain-knowledgeFacial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.IEEE2018-11-27T17:17:03Z2018-11-272018-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfFerreira, P. M., Marques, F., Cardoso, J. S., & Rebelo, A. (2018). Physiological inspired neural networks for emotion recognition,, 6, 53930-53943. doi: 10.1109/ACCESS.2018.2870063. Disponível no Repositório UPT, http://hdl.handle.net/11328/2469http://hdl.handle.net/11328/2469Ferreira, P. M., Marques, F., Cardoso, J. S., & Rebelo, A. (2018). Physiological inspired neural networks for emotion recognition,, 6, 53930-53943. doi: 10.1109/ACCESS.2018.2870063. Disponível no Repositório UPT, http://hdl.handle.net/11328/2469http://hdl.handle.net/11328/2469https://doi.org/10.1109/ACCESS.2018.2870063eng2169-3536https://ieeexplore.ieee.org/document/8472816http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessFerreira, Pedro M.Marques, FilipeCardoso, Jaime S.Rebelo, Anareponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-16T02:05:13Zoai:repositorio.upt.pt:11328/2469Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:39:15.319941Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Physiological inspired neural networks for emotion recognition
title Physiological inspired neural networks for emotion recognition
spellingShingle Physiological inspired neural networks for emotion recognition
Ferreira, Pedro M.
Facial expressions recognition
Convolutional neural networks
Regularization
Domain-knowledge
title_short Physiological inspired neural networks for emotion recognition
title_full Physiological inspired neural networks for emotion recognition
title_fullStr Physiological inspired neural networks for emotion recognition
title_full_unstemmed Physiological inspired neural networks for emotion recognition
title_sort Physiological inspired neural networks for emotion recognition
author Ferreira, Pedro M.
author_facet Ferreira, Pedro M.
Marques, Filipe
Cardoso, Jaime S.
Rebelo, Ana
author_role author
author2 Marques, Filipe
Cardoso, Jaime S.
Rebelo, Ana
author2_role author
author
author
dc.contributor.author.fl_str_mv Ferreira, Pedro M.
Marques, Filipe
Cardoso, Jaime S.
Rebelo, Ana
dc.subject.por.fl_str_mv Facial expressions recognition
Convolutional neural networks
Regularization
Domain-knowledge
topic Facial expressions recognition
Convolutional neural networks
Regularization
Domain-knowledge
description Facial expression recognition (FER) is currently one of the most active research topics due to its wide range of applications in the human-computer interaction field. An important part of the recent success of automatic FER was achieved thanks to the emergence of deep learning approaches. However, training deep networks for FER is still a very challenging task, since most of the available FER data sets are relatively small. Although transfer learning can partially alleviate the issue, the performance of deep models is still below of its full potential as deep features may contain redundant information from the pre-trained domain. Instead, we propose a novel end-to-end neural network architecture along with a well-designed loss function based on the strong prior knowledge that facial expressions are the result of the motions of some facial muscles and components. The loss function is defined to regularize the entire learning process so that the proposed neural network is able to explicitly learn expression-specific features. Experimental results demonstrate the effectiveness of the proposed model in both lab-controlled and wild environments. In particular, the proposed neural network provides quite promising results, outperforming in most cases the current state-of-the-art methods.
publishDate 2018
dc.date.none.fl_str_mv 2018-11-27T17:17:03Z
2018-11-27
2018-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv Ferreira, P. M., Marques, F., Cardoso, J. S., & Rebelo, A. (2018). Physiological inspired neural networks for emotion recognition,, 6, 53930-53943. doi: 10.1109/ACCESS.2018.2870063. Disponível no Repositório UPT, http://hdl.handle.net/11328/2469
http://hdl.handle.net/11328/2469
Ferreira, P. M., Marques, F., Cardoso, J. S., & Rebelo, A. (2018). Physiological inspired neural networks for emotion recognition,, 6, 53930-53943. doi: 10.1109/ACCESS.2018.2870063. Disponível no Repositório UPT, http://hdl.handle.net/11328/2469
http://hdl.handle.net/11328/2469
https://doi.org/10.1109/ACCESS.2018.2870063
identifier_str_mv Ferreira, P. M., Marques, F., Cardoso, J. S., & Rebelo, A. (2018). Physiological inspired neural networks for emotion recognition,, 6, 53930-53943. doi: 10.1109/ACCESS.2018.2870063. Disponível no Repositório UPT, http://hdl.handle.net/11328/2469
url http://hdl.handle.net/11328/2469
https://doi.org/10.1109/ACCESS.2018.2870063
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2169-3536
https://ieeexplore.ieee.org/document/8472816
dc.rights.driver.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134952395112448