Emotion recognition in the wild using deep neural networks and Bayesian classifiers

Basit Öğe Kaydı
dc.authorscopusid57202014367
dc.authorscopusid56537094300
dc.authorscopusid36782998200
dc.authorscopusid55926456100
dc.authorscopusid6701387796
dc.contributor.authorSurace, L.
dc.contributor.authorPatacchiola, M.
dc.contributor.authorSönmez, E.B.
dc.contributor.authorSpataro, W.
dc.contributor.authorCangelosi, A.
dc.date.accessioned2024-07-18T20:17:13Z
dc.date.available2024-07-18T20:17:13Z
dc.date.issued2017
dc.descriptionACM SIGCHIen_US
dc.description19th ACM International Conference on Multimodal Interaction, ICMI 2017 -- 13 November 2017 through 17 November 2017 -- -- 131842en_US
dc.description.abstractGroup emotion recognition in the wild is a challenging problem, due to the unstructured environments in which everyday life pictures are taken. Some of the obstacles for an effective classification are occlusions, variable lighting conditions, and image quality. In this work we present a solution based on a novel combination of deep neural networks and Bayesian classifiers. The neural network works on a bottom-up approach, analyzing emotions expressed by isolated faces. The Bayesian classifier estimates a global emotion integrating top-down features obtained through a scene descriptor. In order to validate the system we tested the framework on the dataset released for the Emotion Recognition in the Wild Challenge 2017. Our method achieved an accuracy of 64.68% on the test set, significantly outperforming the 53.62% competition baseline. © 2017 Association for Computing Machinery.en_US
dc.description.sponsorshipNvidiaen_US
dc.description.sponsorshipWe gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.en_US
dc.identifier.doi10.1145/3136755.3143015
dc.identifier.endpage597en_US
dc.identifier.isbn9781450355438
dc.identifier.scopus2-s2.0-85046769455en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage593en_US
dc.identifier.urihttps://doi.org/10.1145/3136755.3143015
dc.identifier.urihttps://hdl.handle.net/11411/6453
dc.identifier.volume2017-Januaryen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherAssociation for Computing Machinery, Incen_US
dc.relation.ispartofICMI 2017 - Proceedings of the 19th ACM International Conference on Multimodal Interactionen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectBayesian Networksen_US
dc.subjectDeep Neural Networksen_US
dc.subjectEmotiw 2017 Challengeen_US
dc.subjectEnsemble Learningen_US
dc.subjectGroup Emotion Recognitionen_US
dc.subjectBayesian Networksen_US
dc.subjectInteractive Computer Systemsen_US
dc.subjectSpeech Recognitionen_US
dc.subjectBayesian Classifieren_US
dc.subjectBottom Up Approachen_US
dc.subjectEmotion Recognitionen_US
dc.subjectEmotiw 2017 Challengeen_US
dc.subjectEnsemble Learningen_US
dc.subjectGroup Emotionsen_US
dc.subjectUnstructured Environmentsen_US
dc.subjectVariable Lightingsen_US
dc.subjectDeep Neural Networksen_US
dc.titleEmotion recognition in the wild using deep neural networks and Bayesian classifiers
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus Indexed Publications