Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPBW34M/3A3LQGS
Repositorysid.inpe.br/sibgrapi/2011/07.11.01.52
Last Update2011:07.19.13.42.54 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2011/07.11.01.52.29
Metadata Last Update2022:07.30.18.33.19 (UTC) administrator
DOI10.1109/SIBGRAPI.2011.41
Citation KeyLopesSanValAlmAra:2011:TrLeHu
TitleTransfer Learning for Human Action Recognition
FormatDVD, On-line.
Year2011
Access Date2024, Apr. 28
Number of Files1
Size532 KiB
2. Context
Author1 Lopes, Ana Paula B.
2 Santos, Elerson R. da S.
3 Valle, Eduardo A.
4 Almeida, Jussara M. de
5 Araújo, Arnaldo de Albuquerque
Affiliation1 Depart. of Computer Science - Universidade Federal de Minas Gerais (UFMG),Belo Horizonte (MG), Brazil and Depart. of Exact and Tech. Sciences - Universidade Estadual de Santa Cruz (UESC),ilhéus, Brazil
2 Depart. of Computer Science - Universidade Federal de Minas Gerais (UFMG),Belo Horizonte (MG), Brazil
3 Universidade Estadual de Campinas (UNICAMP), Campinas (SP), Brazil
4 Depart. of Computer Science - Universidade Federal de Minas Gerais (UFMG),Belo Horizonte (MG), Brazil
5 Depart. of Computer Science - Universidade Federal de Minas Gerais (UFMG),Belo Horizonte (MG), Brazil
EditorLewiner, Thomas
Torres, Ricardo
e-Mail Addresselerss@gmail.com
Conference NameConference on Graphics, Patterns and Images, 24 (SIBGRAPI)
Conference LocationMaceió, AL, Brazil
Date28-31 Aug. 2011
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2011-07-23 15:36:12 :: elerss@gmail.com -> administrator :: 2011
2022-07-30 18:33:19 :: administrator -> :: 2011
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsaction recognition
transfer learning
bags-of-visual-features
video understanding
AbstractTo manually collect action samples from realistic videos is a time-consuming and error-prone task. This is a serious bottleneck to research related to video understanding, since the large intra-class variations of such videos demand training sets large enough to properly encompass those variations. Most authors dealing with this issue rely on (semi-) automated procedures to collect additional, generally noisy, examples. In this paper, we exploit a different approach, based on a Transfer Learning (TL) technique, to address the target task of action recognition. More specifically, we propose a framework that transfers the knowledge about concepts from a previously labeled still image database to the target action video database. It is assumed that, once identified in the target action database, these concepts provide some contextual clues to the action classifier. Our experiments with Caltech256 and Hollywood2 databases indicate: a) the feasibility of successfully using transfer learning techniques to detect concepts and, b) that it is indeed possible to enhance action recognition with the transferred knowledge of even a few concepts. In our case, only four concepts were enough to obtain statistically significant improvements for most actions.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2011 > Transfer Learning for...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > Transfer Learning for...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 10/07/2011 22:52 0.5 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPBW34M/3A3LQGS
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3A3LQGS
Languageen
Target FilePID1979911.pdf
User Groupelerss@gmail.com
Visibilityshown
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/46SKNPE
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2022/05.15.00.56 2
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