View in EDS

PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition.

Saved in:
Bibliographic Details
Title: PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition.
Authors: Zhao, Mengyi1 (AUTHOR), Dai, Shuling1,2 (AUTHOR) sldai@buaa.edu.cn, Zhu, Yanjun3 (AUTHOR), Tang, Hao4 (AUTHOR), Xie, Pan5 (AUTHOR), Li, Yue5 (AUTHOR), Liu, Chunlei5 (AUTHOR), Zhang, Baochang5 (AUTHOR)
Source: Neurocomputing. Aug2022, Vol. 501, p640-649. 10p.
Subjects: Memory
Abstract: Skeleton-based action recognition is an essential yet challenging visual task, whose accuracy has been remarkably improved due to the successful application of graph convolutional networks (GCNs). However, high computation cost and memory usage hinder their deployment on resource-constrained environment. To deal with the issue, in this paper, we introduce two novel progressive binary graph convolutional network for skeleton-based action recognition PB-GCN and PB-GCN * , which can obtain significant speed-up and memory saving. In PB-GCN, the filters are binarized, and in PB-GCN * , both filters and activations are binary. Specifically, we propose a progressive optimization, i.e., employing ternary models as the initialization of binary GCNs (BGCN) to improve the representational capability of binary models. Moreover, the center loss is exploited to improve the training procedure for better performance. Experimental results on two public benchmarks (i.e., Skeleton-Kinetics and NTU RGB + D) demonstrate that the accuracy of the proposed PB-GCN and PB-GCN * are comparable to their full-precision counterparts and outperforms the state-of-the-art methods, such as BWN, XNOR-Net, and Bi-Real Net. [ABSTRACT FROM AUTHOR]
Copyright of Neurocomputing is the property of Elsevier B.V. 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: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 157909877
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhao%2C+Mengyi%22">Zhao, Mengyi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dai%2C+Shuling%22">Dai, Shuling</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> sldai@buaa.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Yanjun%22">Zhu, Yanjun</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tang%2C+Hao%22">Tang, Hao</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xie%2C+Pan%22">Xie, Pan</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Yue%22">Li, Yue</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Chunlei%22">Liu, Chunlei</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Baochang%22">Zhang, Baochang</searchLink><relatesTo>5</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neurocomputing%22">Neurocomputing</searchLink>. Aug2022, Vol. 501, p640-649. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Memory%22">Memory</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Skeleton-based action recognition is an essential yet challenging visual task, whose accuracy has been remarkably improved due to the successful application of graph convolutional networks (GCNs). However, high computation cost and memory usage hinder their deployment on resource-constrained environment. To deal with the issue, in this paper, we introduce two novel progressive binary graph convolutional network for skeleton-based action recognition PB-GCN and PB-GCN * , which can obtain significant speed-up and memory saving. In PB-GCN, the filters are binarized, and in PB-GCN * , both filters and activations are binary. Specifically, we propose a progressive optimization, i.e., employing ternary models as the initialization of binary GCNs (BGCN) to improve the representational capability of binary models. Moreover, the center loss is exploited to improve the training procedure for better performance. Experimental results on two public benchmarks (i.e., Skeleton-Kinetics and NTU RGB + D) demonstrate that the accuracy of the proposed PB-GCN and PB-GCN * are comparable to their full-precision counterparts and outperforms the state-of-the-art methods, such as BWN, XNOR-Net, and Bi-Real Net. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neurocomputing is the property of Elsevier B.V. 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=egs&AN=157909877
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.neucom.2022.06.070
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 640
    Subjects:
      – SubjectFull: Memory
        Type: general
    Titles:
      – TitleFull: PB-GCN: Progressive binary graph convolutional networks for skeleton-based action recognition.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhao, Mengyi
      – PersonEntity:
          Name:
            NameFull: Dai, Shuling
      – PersonEntity:
          Name:
            NameFull: Zhu, Yanjun
      – PersonEntity:
          Name:
            NameFull: Tang, Hao
      – PersonEntity:
          Name:
            NameFull: Xie, Pan
      – PersonEntity:
          Name:
            NameFull: Li, Yue
      – PersonEntity:
          Name:
            NameFull: Liu, Chunlei
      – PersonEntity:
          Name:
            NameFull: Zhang, Baochang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 28
              M: 08
              Text: Aug2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 09252312
          Numbering:
            – Type: volume
              Value: 501
          Titles:
            – TitleFull: Neurocomputing
              Type: main
ResultId 1