Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'

Recent technological advancements in Artificial Intelligence make it easy to create deepfakes, hyper-realistic videos in which images and video clips are processed to create fake videos that appear authentic. Many of them are based on swapping faces without the consent of the person whose appearance...

ver descrição completa

Detalhes bibliográficos
Autores: García, Roberto, López-Gil, Juan-Miguel, Gil, Rosa
Formato: conjunto de datos
Fecha de publicación:2022
País:España
Recursos:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10459.1/83929
Acesso em linha:https://doi.org/10.34810/data262
Access Level:acceso abierto
Palavra-chave:Computer and Information Science
Affective Computing
Deepfake
Emotion Recognition
id ES_831a16c7eb5bceb02f32b997abe6bbaa
oai_identifier_str oai:recercat.cat:10459.1/83929
network_acronym_str ES
network_name_str España
repository_id_str
spelling Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'García, RobertoLópez-Gil, Juan-MiguelGil, RosaComputer and Information ScienceAffective ComputingDeepfakeEmotion RecognitionRecent technological advancements in Artificial Intelligence make it easy to create deepfakes, hyper-realistic videos in which images and video clips are processed to create fake videos that appear authentic. Many of them are based on swapping faces without the consent of the person whose appearance and voice are used. As emotions are inherent in human communication, studying how deepfakes transfer emotional expressions from original to fakes is relevant. In this work, we conduct an in-depth study on facial emotional expression in deepfakes using a well-known face swap-based deepfake database. First, we extracted the photograms from their videos. Then, we analyzed the emotional expression in both the original and the faked versions of the video recordings for all performers in the database. Results show that emotional expressions are not adequately transferred between original recordings and the deepfakes created from them. The high variability in emotions and performers detected between original and fake recordings indicates that performer emotion expressiveness should be considered for better deepfake generation or for detecting them.CORA.Repositori de Dades de RecercaGarcía, Roberto2022info:eu-repo/semantics/datasethttps://doi.org/10.34810/data262reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/semantics/openAccessCC0 1.0oai:recercat.cat:10459.1/839292026-05-29T05:05:01Z
dc.title.none.fl_str_mv Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
title Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
spellingShingle Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
García, Roberto
Computer and Information Science
Affective Computing
Deepfake
Emotion Recognition
title_short Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
title_full Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
title_fullStr Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
title_full_unstemmed Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
title_sort Replication Data for: 'Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression'
dc.creator.none.fl_str_mv García, Roberto
López-Gil, Juan-Miguel
Gil, Rosa
author García, Roberto
author_facet García, Roberto
López-Gil, Juan-Miguel
Gil, Rosa
author_role author
author2 López-Gil, Juan-Miguel
Gil, Rosa
author2_role author
author
dc.contributor.none.fl_str_mv García, Roberto
dc.subject.none.fl_str_mv Computer and Information Science
Affective Computing
Deepfake
Emotion Recognition
topic Computer and Information Science
Affective Computing
Deepfake
Emotion Recognition
description Recent technological advancements in Artificial Intelligence make it easy to create deepfakes, hyper-realistic videos in which images and video clips are processed to create fake videos that appear authentic. Many of them are based on swapping faces without the consent of the person whose appearance and voice are used. As emotions are inherent in human communication, studying how deepfakes transfer emotional expressions from original to fakes is relevant. In this work, we conduct an in-depth study on facial emotional expression in deepfakes using a well-known face swap-based deepfake database. First, we extracted the photograms from their videos. Then, we analyzed the emotional expression in both the original and the faked versions of the video recordings for all performers in the database. Results show that emotional expressions are not adequately transferred between original recordings and the deepfakes created from them. The high variability in emotions and performers detected between original and fake recordings indicates that performer emotion expressiveness should be considered for better deepfake generation or for detecting them.
publishDate 2022
dc.date.none.fl_str_mv 2022
dc.type.none.fl_str_mv info:eu-repo/semantics/dataset
format dataset
dc.identifier.none.fl_str_mv https://doi.org/10.34810/data262
url https://doi.org/10.34810/data262
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
CC0 1.0
eu_rights_str_mv openAccess
rights_invalid_str_mv CC0 1.0
dc.publisher.none.fl_str_mv CORA.Repositori de Dades de Recerca
publisher.none.fl_str_mv CORA.Repositori de Dades de Recerca
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412109420331008
score 15.198674

Registos relacionados