Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/43B8A7P
Repositorysid.inpe.br/sibgrapi/2020/09.28.22.29
Last Update2020:09.28.22.29.43 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2020/09.28.22.29.43
Metadata Last Update2022:06.14.00.00.10 (UTC) administrator
DOI10.1109/SIBGRAPI51738.2020.00051
Citation KeySchirmer:2020:Li2DPo
TitleA lightweight 2D Pose Machine with attention enhancement
FormatOn-line
Year2020
Access Date2024, May 04
Number of Files1
Size7396 KiB
2. Context
AuthorSchirmer, Luiz
AffiliationPUC-rio
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
e-Mail Addressschirmer.luizj@gmail.com
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationPorto de Galinhas (virtual)
Date7-10 Nov. 2020
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2020-09-28 22:29:43 :: schirmer.luizj@gmail.com -> administrator ::
2022-06-14 00:00:10 :: administrator -> schirmer.luizj@gmail.com :: 2020
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordspose estimation
tensor decompostion
attention layer
AbstractPose estimation is a challenging task in computer vision that has many applications, as for example: in motion capture, in medical analysis, in human posture monitoring, and in robotics. In other words, it is a main tool to enable machines do understand human patterns in videos or images. Performing this task in real-time while maintaining accuracy and precision is critical for many of these applications. Several papers propose real time approaches considering deep neural networks for pose estimation. However, in most cases they fail when considering run-time performance or do not achieve the precision needed. In this work, we propose a new model for real-time pose estimation considering attention modules for convolutional neural networks (CNNs). We introduce a two-dimensional relative attention mechanism for feature extraction in pose machines leading to improvements in accuracy. We create a single shot architecture where both operations to infer keypoints and part affinity fields share the information. Also, for each stage, we use tensor decompositions to not only reduce dimensionality, but also to improve performance. This allows us to factorize each convolution and drastically reduce the number of parameters in our network. Our experiments show that, with this factorized approach, it is possible to achieve state-of-art performance in terms of run-time while we have a small reduction in accuracy.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2020 > A lightweight 2D...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > A lightweight 2D...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 28/09/2020 19:29 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/43B8A7P
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/43B8A7P
Languageen
Target FilePose_estimation_for_Sibgrapi_2020.pdf
User Groupschirmer.luizj@gmail.com
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/43G4L9S
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2020/10.28.20.46 8
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination 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
7. Description control
e-Mail (login)schirmer.luizj@gmail.com
update 


Close