Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPAW/3PJFC5L
Repositorysid.inpe.br/sibgrapi/2017/09.07.01.51
Last Update2017:09.07.01.51.40 administrator
Metadatasid.inpe.br/sibgrapi/2017/09.07.01.51.40
Metadata Last Update2021:02.23.03.53.29 administrator
Citation KeyPerezTestRoch:2017:ViPoDe
TitleVideo pornography detection through deep learning techniques and motion information
FormatOn-line
Year2017
Access Date2021, Mar. 02
Number of Files1
Size1168 KiB
Context area
Author1 Perez, Mauricio Lisboa
2 Testoni, Vanessa
3 Rocha, Anderson
Affiliation1 EEE - NTU
2 Samsung Research Institute Brazil
3 IC - UNICAMP
EditorTorchelsen, Rafael Piccin
Nascimento, Erickson Rangel do
Panozzo, Daniele
Liu, Zicheng
Farias, Mylène
Viera, Thales
Sacht, Leonardo
Ferreira, Nivan
Comba, João Luiz Dihl
Hirata, Nina
Schiavon Porto, Marcelo
Vital, Creto
Pagot, Christian Azambuja
Petronetto, Fabiano
Clua, Esteban
Cardeal, Flávio
e-Mail Addressmauriciolp84@gmail.com
Conference NameConference on Graphics, Patterns and Images, 30 (SIBGRAPI)
Conference LocationNiterói, RJ
DateOct. 17-20, 2017
Book TitleProceedings
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
Tertiary TypeMaster's or Doctoral Work
History2017-09-07 01:51:40 :: mauriciolp84@gmail.com -> administrator ::
2021-02-23 03:53:29 :: administrator -> :: 2017
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
KeywordsPornography classification, Deep learning and motion information, Optical flow, MPEG motion vectors, Sensitive video classification.
AbstractRecent literature has explored automated pornographic detection - a bold move to replace humans in the tedious task of moderating online content. Unfortunately, on scenes with high skin exposure, such as people sunbathing and wrestling, the state of the art can have many false alarms. This paper is based on the premise that incorporating motion information in the models can alleviate the problem of mapping skin exposure to pornographic content, and advances the bar on automated pornography detection with the use of motion information and deep learning architectures. Deep Learning, especially in the form of Convolutional Neural Networks, have striking results on computer vision, but their potential for pornography detection is yet to be fully explored through the use of motion information. We propose novel ways for combining static (picture) and dynamic (motion) information using optical flow and MPEG motion vectors. We show that both methods provide equivalent accuracies, but that MPEG motion vectors allow a more efficient implementation. The best proposed method yields a classification accuracy of 97.9% - an error reduction of 64.4% when compared to the state of the art - on a dataset of 800 challenging test cases. Finally, we present and discuss results on a larger, and more challenging, dataset.
ArrangementSIBGRAPI 2017 > Video pornography detection...
source Directory Contentthere are no files
agreement Directory Content
agreement.html 06/09/2017 22:51 1.2 KiB 
Conditions of access and use area
data URLhttp://urlib.net/rep/8JMKD3MGPAW/3PJFC5L
zipped data URLhttp://urlib.net/zip/8JMKD3MGPAW/3PJFC5L
Languageen
Target Filewtd-sibgrapi.pdf
User Groupmauriciolp84@gmail.com
Visibilityshown
Update Permissionnot transferred
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPAW/3PKCC58
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume

Close