Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPBW34M/3EEGUEH
Repositorysid.inpe.br/sibgrapi/2013/07.11.03.52
Last Update2013:07.11.03.52.12 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2013/07.11.03.52.12
Metadata Last Update2022:07.30.18.33.24 (UTC) administrator
DOI10.1109/SIBGRAPI.2013.52
Citation KeyMotaSouzAraúViei:2013:CoOrTe
TitleCombining Orientation Tensors for Human Action Recognition
FormatOn-line.
Year2013
Access Date2024, Apr. 29
Number of Files1
Size1080 KiB
2. Context
Author1 Mota, Virgínia Fernandes
2 Souza, Jéssica Ione Conceição
3 Araújo, Arnaldo de Albuquerque
4 Vieira, Marcelo Bernardes
Affiliation1 Universidade Federal de Minas Gerais
2 Universidade Federal de Minas Gerais
3 Universidade Federal de Minas Gerais
4 Universidade Federal de Juiz de Fora
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
Date5-8 Aug. 2013
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2013-07-11 03:52:12 :: virginiafernandesmota@gmail.com -> administrator ::
2022-07-30 18:33:24 :: administrator -> :: 2013
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
KeywordsHistogram of gradients
Orientation tensor
Motion description
Human action recognition
AbstractThis paper presents a new tensor motion descriptor based on histogram of oriented gradients. We model the temporal evolution of gradient distribution with orientation tensors in equally sized blocks throughout the video sequence. Subsequently, these blocks are concatenated to create the final descriptor. Using a SVM classifier, even without any bag-of-feature based approach, our method achieves recognition rates greater than those found by other HOG techniques on KTH dataset and a competitive recognition rate for UCF11 and Hollywood2 datasets.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2013 > Combining Orientation Tensors...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Combining Orientation Tensors...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 11/07/2013 00:52 0.7 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPBW34M/3EEGUEH
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3EEGUEH
Languageen
Target Filepaper_mota_114911.pdf
User Groupvirginiafernandesmota@gmail.com
Visibilityshown
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/46SLB4P
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2022/05.15.04.02 7
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume


Close