View in EDS PDF Full Text

Decoupled Global-Local Collaborative Network for Visual Question Answering.

Saved in:
Bibliographic Details
Title: Decoupled Global-Local Collaborative Network for Visual Question Answering.
Authors: Zhou, Ganlong1 ganlongzhou@163.com, Han, Dezhi1 dzhan@shmtu.edu.cn, Shen, Xiang1,2 xiang.shen@sydney.edu.au, Xin, Xiaoqi1
Source: Computer Science & Information Systems. Sep2026, Vol. 23 Issue 4, p1259-1286. 28p.
Subjects: Visual discrimination
Abstract: Visual Question Answering (VQA) aims to achieve cross-modal semantic understanding through joint modeling of visual content and natural language. Although existing attention-based approaches effectively align features, they struggle to simultaneously accommodate global semantic modeling and local fine-grained perception within single-path architectures, leading to semantic drift and underutilization of information when addressing multi-perspective reasoning tasks. To mitigate this limitation, we propose a Decoupled Global-Local Collaborative Network (DGL-Net) that structurally partitions the cross-modal reasoning process into two complementary branches: global semantic understanding and local fine-grained modeling. Specifically, the global branch employs hierarchical attention fusion to model long-range dependencies and holistic scene semantics, providing contextual constraints for reasoning. The local branch introduces semantic relation enhancement and relevant region screening to explicitly model intra-modal structural relationships, strengthening fine-grained region-word alignment by injecting structural information. During training and inference, a branch-decoupling and collaborative fusion strategy enables independent yet complementary feature learning. Extensive experimental results demonstrate accuracies of 72.15% and 57.87% on VQA-v2 and GQA benchmarks, respectively. Notably, the proposed method exhibits enhanced robustness and generalization in complex semantic and compositional reasoning tasks, validating the efficacy of the decoupled collaborative strategy. [ABSTRACT FROM AUTHOR]
Copyright of Computer Science & Information Systems is the property of ComSIS Consortium 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 Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 197881220
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Decoupled Global-Local Collaborative Network for Visual Question Answering.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhou%2C+Ganlong%22">Zhou, Ganlong</searchLink><relatesTo>1</relatesTo><i> ganlongzhou@163.com</i><br /><searchLink fieldCode="AR" term="%22Han%2C+Dezhi%22">Han, Dezhi</searchLink><relatesTo>1</relatesTo><i> dzhan@shmtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Shen%2C+Xiang%22">Shen, Xiang</searchLink><relatesTo>1,2</relatesTo><i> xiang.shen@sydney.edu.au</i><br /><searchLink fieldCode="AR" term="%22Xin%2C+Xiaoqi%22">Xin, Xiaoqi</searchLink><relatesTo>1</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Science+%26+Information+Systems%22">Computer Science & Information Systems</searchLink>. Sep2026, Vol. 23 Issue 4, p1259-1286. 28p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Visual+discrimination%22">Visual discrimination</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Visual Question Answering (VQA) aims to achieve cross-modal semantic understanding through joint modeling of visual content and natural language. Although existing attention-based approaches effectively align features, they struggle to simultaneously accommodate global semantic modeling and local fine-grained perception within single-path architectures, leading to semantic drift and underutilization of information when addressing multi-perspective reasoning tasks. To mitigate this limitation, we propose a Decoupled Global-Local Collaborative Network (DGL-Net) that structurally partitions the cross-modal reasoning process into two complementary branches: global semantic understanding and local fine-grained modeling. Specifically, the global branch employs hierarchical attention fusion to model long-range dependencies and holistic scene semantics, providing contextual constraints for reasoning. The local branch introduces semantic relation enhancement and relevant region screening to explicitly model intra-modal structural relationships, strengthening fine-grained region-word alignment by injecting structural information. During training and inference, a branch-decoupling and collaborative fusion strategy enables independent yet complementary feature learning. Extensive experimental results demonstrate accuracies of 72.15% and 57.87% on VQA-v2 and GQA benchmarks, respectively. Notably, the proposed method exhibits enhanced robustness and generalization in complex semantic and compositional reasoning tasks, validating the efficacy of the decoupled collaborative strategy. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Computer Science & Information Systems is the property of ComSIS Consortium 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=197881220
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.2298/CSIS260403039Z
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 1259
    Subjects:
      – SubjectFull: Visual discrimination
        Type: general
    Titles:
      – TitleFull: Decoupled Global-Local Collaborative Network for Visual Question Answering.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhou, Ganlong
      – PersonEntity:
          Name:
            NameFull: Han, Dezhi
      – PersonEntity:
          Name:
            NameFull: Shen, Xiang
      – PersonEntity:
          Name:
            NameFull: Xin, Xiaoqi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 18200214
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Computer Science & Information Systems
              Type: main
ResultId 1