DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition

[EN] The identification of sexual activities in images can be helpful in detecting the level of content severity and can assist pornography detectors in filtering specific types of content. In this paper, we propose a Deep Learning-based framework, named DeepHSAR, for semi-supervised fine-grained mu...

ver descrição completa

Detalhes bibliográficos
Autores: Kumar, Abhishek Gangwar, González Castro, Víctor, Alegre Gutiérrez, Enrique, Fidalgo Fernández, Eduardo, Martínez Mendoza, Alicia
Formato: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2024
País:España
Recursos:Universidad de León
Repositorio:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:buleria.unileon.es:10612/23230
Acesso em linha:https://hdl.handle.net/10612/23230
Access Level:acceso abierto
Palavra-chave:Informática
Ingeniería de sistemas
Multi-label classification
Sexual activity detection
Fine-grained classification
Semi-supervised classification
Pornography detection
1203.04 Inteligencia Artificial
1203.17 Informática
1209.03 Análisis de Datos
2209.90 Tratamiento Digital. Imágenes
id ES_67cff69296ed98da0dc636133e941bb2
oai_identifier_str oai:buleria.unileon.es:10612/23230
network_acronym_str ES
network_name_str España
repository_id_str
spelling DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognitionKumar, Abhishek GangwarGonzález Castro, VíctorAlegre Gutiérrez, EnriqueFidalgo Fernández, EduardoMartínez Mendoza, AliciaInformáticaIngeniería de sistemasMulti-label classificationSexual activity detectionFine-grained classificationSemi-supervised classificationPornography detection1203.04 Inteligencia Artificial1203.17 Informática1209.03 Análisis de Datos2209.90 Tratamiento Digital. Imágenes[EN] The identification of sexual activities in images can be helpful in detecting the level of content severity and can assist pornography detectors in filtering specific types of content. In this paper, we propose a Deep Learning-based framework, named DeepHSAR, for semi-supervised fine-grained multi-label Human Sexual Activity Recognition (HSAR). To the best of our knowledge, this is the first work to propose an approach to HSAR. We also introduce a new multi-label dataset, named SexualActs-150k, containing 150k images manually labeled with 19 types of sexual activities. DeepHSAR has two multi-label classification streams: one for global image representation and another for fine-grained representation. To perform fine-grained image classification without ground-truth bounding box annotations, we propose a novel semi-supervised approach for multi-label fine-grained recognition, which learns through an iterative clustering and iterative CNN training process. We obtained a significant performance gain by fusing both streams (i.e., overall F1-score of 79.29%), compared to when they work separately. The experiments demonstrate that the proposed framework explicitly outperforms baseline and state-of-the-art approaches. In addition, the proposed framework also obtains state-of-the-art or competitive results in semi-supervised multi-label learning experiments on the NUS-WIDE and MS-COCO datasets with overall F1-scores of 75.98% and 85.17%, respectively. Furthermore, the proposed DeepHSAR has been assessed on the NPDI Pornography-2k video dataset, achieving a new state-of-the-art with 99.85% accuracy.SIThis research has been funded with support from the European Union\u2019s Horizon 2020 Research and Innovation Framework Programme, H2020 SU-FCT-2019 under the GRACE project with Grant Agreement 883341 . This publication reflects the views only of the authors, and the European Union\u2019s Horizon 2020 Research and Innovation Framework Programme, H2020 SU-FCT-2019 cannot be held responsible for any use which may be made of the information contained therein.European CommissionElsevierIngenieria de Sistemas y AutomaticaEscuela de Ingenierias Industrial, Informática y Aeroespacial2024infoinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionhttps://hdl.handle.net/10612/23230reponame:BULERIA. Repositorio Institucional de la Universidad de Leóninstname:Universidad de LeónInglésinfo:eu-repo/grantAgreement/EC/H2020/883341http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:buleria.unileon.es:10612/232302026-06-24T12:43:27Z
dc.title.none.fl_str_mv DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
title DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
spellingShingle DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
Kumar, Abhishek Gangwar
Informática
Ingeniería de sistemas
Multi-label classification
Sexual activity detection
Fine-grained classification
Semi-supervised classification
Pornography detection
1203.04 Inteligencia Artificial
1203.17 Informática
1209.03 Análisis de Datos
2209.90 Tratamiento Digital. Imágenes
title_short DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
title_full DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
title_fullStr DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
title_full_unstemmed DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
title_sort DeepHSAR: Semi-supervised fine-grained learning for multi-label human sexual activity recognition
dc.creator.none.fl_str_mv Kumar, Abhishek Gangwar
González Castro, Víctor
Alegre Gutiérrez, Enrique
Fidalgo Fernández, Eduardo
Martínez Mendoza, Alicia
author Kumar, Abhishek Gangwar
author_facet Kumar, Abhishek Gangwar
González Castro, Víctor
Alegre Gutiérrez, Enrique
Fidalgo Fernández, Eduardo
Martínez Mendoza, Alicia
author_role author
author2 González Castro, Víctor
Alegre Gutiérrez, Enrique
Fidalgo Fernández, Eduardo
Martínez Mendoza, Alicia
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Ingenieria de Sistemas y Automatica
Escuela de Ingenierias Industrial, Informática y Aeroespacial
dc.subject.none.fl_str_mv Informática
Ingeniería de sistemas
Multi-label classification
Sexual activity detection
Fine-grained classification
Semi-supervised classification
Pornography detection
1203.04 Inteligencia Artificial
1203.17 Informática
1209.03 Análisis de Datos
2209.90 Tratamiento Digital. Imágenes
topic Informática
Ingeniería de sistemas
Multi-label classification
Sexual activity detection
Fine-grained classification
Semi-supervised classification
Pornography detection
1203.04 Inteligencia Artificial
1203.17 Informática
1209.03 Análisis de Datos
2209.90 Tratamiento Digital. Imágenes
description [EN] The identification of sexual activities in images can be helpful in detecting the level of content severity and can assist pornography detectors in filtering specific types of content. In this paper, we propose a Deep Learning-based framework, named DeepHSAR, for semi-supervised fine-grained multi-label Human Sexual Activity Recognition (HSAR). To the best of our knowledge, this is the first work to propose an approach to HSAR. We also introduce a new multi-label dataset, named SexualActs-150k, containing 150k images manually labeled with 19 types of sexual activities. DeepHSAR has two multi-label classification streams: one for global image representation and another for fine-grained representation. To perform fine-grained image classification without ground-truth bounding box annotations, we propose a novel semi-supervised approach for multi-label fine-grained recognition, which learns through an iterative clustering and iterative CNN training process. We obtained a significant performance gain by fusing both streams (i.e., overall F1-score of 79.29%), compared to when they work separately. The experiments demonstrate that the proposed framework explicitly outperforms baseline and state-of-the-art approaches. In addition, the proposed framework also obtains state-of-the-art or competitive results in semi-supervised multi-label learning experiments on the NUS-WIDE and MS-COCO datasets with overall F1-scores of 75.98% and 85.17%, respectively. Furthermore, the proposed DeepHSAR has been assessed on the NPDI Pornography-2k video dataset, achieving a new state-of-the-art with 99.85% accuracy.
publishDate 2024
dc.date.none.fl_str_mv 2024
info
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10612/23230
url https://hdl.handle.net/10612/23230
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/EC/H2020/883341
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:BULERIA. Repositorio Institucional de la Universidad de León
instname:Universidad de León
instname_str Universidad de León
reponame_str BULERIA. Repositorio Institucional de la Universidad de León
collection BULERIA. Repositorio Institucional de la Universidad de León
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409916812263424
score 15.812429

Registos relacionados