View in EDS HTML Full Text PDF Full Text

An efficient sparse pruning method for human pose estimation.

Saved in:
Bibliographic Details
Title: An efficient sparse pruning method for human pose estimation.
Authors: Wang, Mingyang (AUTHOR), Sun, Tianyi (AUTHOR), Song, Kang (AUTHOR), Li, Shuang (AUTHOR), Jiang, Jing (AUTHOR), Sun, Linjun (AUTHOR)
Source: Connection Science. Dec2022, Vol. 34 Issue 1, p960-974. 15p.
Subjects: Computer vision, Human beings
Abstract: Human pose estimation (HPE) is crucial for computer vision (CV). Moreover, it's a vital step for computers to understand human actions and behaviours. However, the huge number of parameters and calculations in the HPE model have brought big challenges to deploy to resource-constrained mobile devices. Aiming to overcome the challenge, we propose a sparse pruning method (SPM) for the HPE model. First, L1 regularisation is added in the training phase of the original model, and network parameters of the convolution layers (CLs) and batch normalisation layers (BNLs) are sparsely trained to obtain a network structure with sparse weights. We then combine the sparse weights of filters with the scaling parameters of the BNLs to determine their importance. Finally, the structured pruning method is used to prune the sparse filters and corresponding channels. SPM can reduce the number of model parameters and calculations without affecting precision. Promising results indicate that SPM outperforms other advanced pruning methods. [ABSTRACT FROM AUTHOR]
Copyright of Connection Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 164286334
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: An efficient sparse pruning method for human pose estimation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wang%2C+Mingyang%22">Wang, Mingyang</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Tianyi%22">Sun, Tianyi</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Song%2C+Kang%22">Song, Kang</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Shuang%22">Li, Shuang</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jiang%2C+Jing%22">Jiang, Jing</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Linjun%22">Sun, Linjun</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Connection+Science%22">Connection Science</searchLink>. Dec2022, Vol. 34 Issue 1, p960-974. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Human+beings%22">Human beings</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Human pose estimation (HPE) is crucial for computer vision (CV). Moreover, it's a vital step for computers to understand human actions and behaviours. However, the huge number of parameters and calculations in the HPE model have brought big challenges to deploy to resource-constrained mobile devices. Aiming to overcome the challenge, we propose a sparse pruning method (SPM) for the HPE model. First, L1 regularisation is added in the training phase of the original model, and network parameters of the convolution layers (CLs) and batch normalisation layers (BNLs) are sparsely trained to obtain a network structure with sparse weights. We then combine the sparse weights of filters with the scaling parameters of the BNLs to determine their importance. Finally, the structured pruning method is used to prune the sparse filters and corresponding channels. SPM can reduce the number of model parameters and calculations without affecting precision. Promising results indicate that SPM outperforms other advanced pruning methods. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Connection Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=pbh&AN=164286334
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/09540091.2021.2012423
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 960
    Subjects:
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Human beings
        Type: general
    Titles:
      – TitleFull: An efficient sparse pruning method for human pose estimation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wang, Mingyang
      – PersonEntity:
          Name:
            NameFull: Sun, Tianyi
      – PersonEntity:
          Name:
            NameFull: Song, Kang
      – PersonEntity:
          Name:
            NameFull: Li, Shuang
      – PersonEntity:
          Name:
            NameFull: Jiang, Jing
      – PersonEntity:
          Name:
            NameFull: Sun, Linjun
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 09540091
          Numbering:
            – Type: volume
              Value: 34
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Connection Science
              Type: main
ResultId 1