Close
Metadata

Identity statement area
Reference TypeConference Proceedings
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/3U2NP8L
Repositorysid.inpe.br/sibgrapi/2019/09.10.17.27
Last Update2019:09.10.17.27.20 administrator
Metadatasid.inpe.br/sibgrapi/2019/09.10.17.27.20
Metadata Last Update2020:02.19.01.58.23 administrator
Citation KeyLaranjeiraLaceNasc:2019:MoCoOb
TitleOn Modeling Context from Objects with a Long Short-Term Memory for Indoor Scene Recognition
FormatOn-line
Year2019
DateOct. 28 - 31, 2019
Access Date2020, Dec. 04
Number of Files1
Size1627 KiB
Context area
Author1 Laranjeira, Camila
2 Lacerda, Anisio
3 Nascimento, Erickson R.
Affiliation1 Universidade Federal de Minas Gerais
2 Universidade Federal de Minas Gerais
3 Universidade Federal de Minas Gerais
EditorOliveira, Luciano Reboušas de
Sarder, Pinaki
Lage, Marcos
Sadlo, Filip
e-Mail Addressmila.laranjeira@gmail.com
Conference NameConference on Graphics, Patterns and Images, 32 (SIBGRAPI)
Conference LocationRio de Janeiro, RJ, Brazil
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
History2019-09-10 17:27:20 :: mila.laranjeira@gmail.com -> administrator ::
2020-02-19 01:58:23 :: administrator -> mila.laranjeira@gmail.com :: 2019
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Document Stagenot transferred
Transferable1
Content TypeExternal Contribution
Tertiary TypeFull Paper
KeywordsIndoor Scene Recognition, Recurrent Neural Networks.
AbstractRecognizing indoor scenes is still regarded an open challenge on the Computer Vision field. Indoor scenes can be well represented by their composing objects, which can vary in angle, appearance, besides often being partially occluded. Even though Convolutional Neural Networks are remarkable for image-related problems, the top performances on indoor scenes are from approaches modeling the intricate relationship of objects. Knowing that Recurrent Neural Networks were designed to model structure from a given sequence, we propose representing an image as a sequence of object-level information in order to feed a bidirectional Long Short-Term Memory network trained for scene classification. We perform a Many-to-Many training approach, such that each element outputs a scene prediction, allowing us to use each prediction to boost recognition. Our method outperforms RNN-based approaches on MIT67, an entirely indoor dataset, while also improved over the most successful methods through an ensemble of classifiers.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 10/09/2019 14:27 1.2 KiB 
Conditions of access and use area
Languageen
Target FilePID6127653.pdf
e-Mail (login)mila.laranjeira@gmail.com
User Groupmila.laranjeira@gmail.com
Visibilityshown
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/3UA4FNL
8JMKD3MGPEW34M/3UA4FPS
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber 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
Description control area
update 

Close