Close
Metadata

Identity statement area
Reference TypeConference Proceedings
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPBW34M/3EEH5B2
Repositorysid.inpe.br/sibgrapi/2013/07.11.04.39
Last Update2013:07.11.04.39.29 virginiafernandesmota@gmail.com
Metadatasid.inpe.br/sibgrapi/2013/07.11.04.39.29
Metadata Last Update2020:02.19.03.09.22 administrator
Citation KeySadMotMacVieAra:2013:TeMoDe
TitleA Tensor Motion Descriptor Based on Multiple Gradient Estimators
FormatOn-line.
Year2013
DateAug. 5-8, 2013
Access Date2020, Dec. 03
Number of Files1
Size241 KiB
Context area
Author1 Sad, Dhiego
2 Mota, Virgínia Fernandes
3 Maciel, Luiz Maurílio
4 Vieira, Marcelo Bernardes
5 Araújo, Arnaldo de Albuquerque
Affiliation1 Universidade Federal de Juiz de Fora
2 Universidade Federal de Minas Gerais
3 Universidade Federal de Juiz de Fora
4 Universidade Federal de Juiz de Fora
5 Universidade Federal de Minas Gerais
EditorBoyer, Kim
Hirata, Nina
Nedel, Luciana
Silva, Claudio
e-Mail Addressvirginiafernandesmota@gmail.com
Conference NameConference on Graphics, Patterns and Images, 26 (SIBGRAPI)
Conference LocationArequipa, Peru
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
History2013-07-11 04:39:29 :: virginiafernandesmota@gmail.com -> administrator ::
2020-02-19 03:09:22 :: administrator -> :: 2013
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Transferable1
Content TypeExternal Contribution
Tertiary TypeFull Paper
KeywordsMultifilter analysis, Motion descriptor, Orientation tensor, Human action recognition.
AbstractThis work presents a novel approach for motion description in videos using multiple band-pass filters which act as first order derivative estimators. The filters response on each frame are coded into individual histograms of gradients to reduce their dimensionality. They are combined using orientation tensors. No local features are extracted and no learning is performed, i.e., the descriptor depends uniquely on the input video. Motion description can be enhanced even using multiple filters with similar or overlapping frequency response. For the problem of human action recognition using the KTH database, our descriptor achieved the recognition rate of 93.3% using three Daubechies filters, one extra filter designed to correlate them, two-fold protocol and a SVM classifier. It is superior to most global descriptor approaches and fairly comparable to the state- of-the-art methods.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 11/07/2013 01:39 0.7 KiB 
Conditions of access and use area
Languageen
Target Filepaper_sad_114944.pdf
User Groupvirginiafernandesmota@gmail.com
Visibilityshown
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition nexthigherunit 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