Emotion recognition in the wild using deep neural networks and Bayesian classifiers
Küçük Resim Yok
Tarih
2017
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Association for Computing Machinery, Inc
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Group 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.
Açıklama
ACM SIGCHI
19th ACM International Conference on Multimodal Interaction, ICMI 2017 -- 13 November 2017 through 17 November 2017 -- -- 131842
19th ACM International Conference on Multimodal Interaction, ICMI 2017 -- 13 November 2017 through 17 November 2017 -- -- 131842
Anahtar Kelimeler
Bayesian Networks, Deep Neural Networks, Emotiw 2017 Challenge, Ensemble Learning, Group Emotion Recognition, Bayesian Networks, Interactive Computer Systems, Speech Recognition, Bayesian Classifier, Bottom Up Approach, Emotion Recognition, Emotiw 2017 Challenge, Ensemble Learning, Group Emotions, Unstructured Environments, Variable Lightings, Deep Neural Networks
Kaynak
ICMI 2017 - Proceedings of the 19th ACM International Conference on Multimodal Interaction
WoS Q Değeri
Scopus Q Değeri
N/A
Cilt
2017-January
