View in EDS

Prospective Layout-Guided Multi-Modal Online Hashing.

Saved in:
Bibliographic Details
Title: Prospective Layout-Guided Multi-Modal Online Hashing.
Authors: Tu, Rong-Cheng1 turongcheng@gmail.com, Mao, Xian-Ling1 maoxl@bit.edu.cn, Liu, Jin-Yu1 liujinyu1229@gmail.com, Ma, Zi-Ao1 maziaoylwt@gmail.com, Lan, Tian1 lantiangmftby@gmail.com, Huang, Heyan1 hhy63@bit.edu.cn
Source: IEEE Transactions on Image Processing. 2025, Vol. 34, p5935-5947. 13p.
Subjects: Hashing, Electronic file management, Message authentication codes, Electronic data processing, Information storage & retrieval systems
Abstract: In real-world scenarios, the data usually appears in a streaming fashion. To achieve remarkable retrieval performance in such scenarios, online multi-modal hashing has drawn great research attention due to its high retrieval speed and low storage cost. However, existing online multi-modal hashing methods still fail to achieve satisfactory retrieval performance in the scenarios where the new streaming datapoints all belong to the new classes. Therefore, to further improve the retrieval performance in these scenarios, we propose a novel Prospective Layout-Guided Multi-modal Online Hashing, termed PLG-MOH. Specifically, PLG-MOH first establishes the layout of the Hamming space by generating a series of hashing centers to split the space. Each hashing center will be gradually assigned to a new appearing class, and these assigned centers correspond one-to-one with the classes. Moreover, we propose a novel prospective layout-guided loss, which leverages all the hashing centers, including those not yet assigned to the classes, to supervise the training of hashing model. As the unassigned hashing centers will be designated to the new classes emerging in the future, it signifies that during each round of training, PLG-MOH has already considered the forthcoming data from new classes in the future rounds. Consequently, PLG-MOH can effectively adapt its hashing functions to address the new arriving samples and learn semantic similarity-preserved hash codes for them, meanwhile it can effectively retain the information learned from the old data. Extensive experiments on two public datasets demonstrate that the proposed PLG-MOH achieves better retrieval performance than state-of-the-art baselines on online scenarios. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Image Processing is the property of IEEE 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: 191897226
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Prospective Layout-Guided Multi-Modal Online Hashing.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Tu%2C+Rong-Cheng%22">Tu, Rong-Cheng</searchLink><relatesTo>1</relatesTo><i> turongcheng@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Mao%2C+Xian-Ling%22">Mao, Xian-Ling</searchLink><relatesTo>1</relatesTo><i> maoxl@bit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Jin-Yu%22">Liu, Jin-Yu</searchLink><relatesTo>1</relatesTo><i> liujinyu1229@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Ma%2C+Zi-Ao%22">Ma, Zi-Ao</searchLink><relatesTo>1</relatesTo><i> maziaoylwt@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Lan%2C+Tian%22">Lan, Tian</searchLink><relatesTo>1</relatesTo><i> lantiangmftby@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Huang%2C+Heyan%22">Huang, Heyan</searchLink><relatesTo>1</relatesTo><i> hhy63@bit.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Image+Processing%22">IEEE Transactions on Image Processing</searchLink>. 2025, Vol. 34, p5935-5947. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Hashing%22">Hashing</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+file+management%22">Electronic file management</searchLink><br /><searchLink fieldCode="DE" term="%22Message+authentication+codes%22">Message authentication codes</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+data+processing%22">Electronic data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Information+storage+%26+retrieval+systems%22">Information storage & retrieval systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In real-world scenarios, the data usually appears in a streaming fashion. To achieve remarkable retrieval performance in such scenarios, online multi-modal hashing has drawn great research attention due to its high retrieval speed and low storage cost. However, existing online multi-modal hashing methods still fail to achieve satisfactory retrieval performance in the scenarios where the new streaming datapoints all belong to the new classes. Therefore, to further improve the retrieval performance in these scenarios, we propose a novel Prospective Layout-Guided Multi-modal Online Hashing, termed PLG-MOH. Specifically, PLG-MOH first establishes the layout of the Hamming space by generating a series of hashing centers to split the space. Each hashing center will be gradually assigned to a new appearing class, and these assigned centers correspond one-to-one with the classes. Moreover, we propose a novel prospective layout-guided loss, which leverages all the hashing centers, including those not yet assigned to the classes, to supervise the training of hashing model. As the unassigned hashing centers will be designated to the new classes emerging in the future, it signifies that during each round of training, PLG-MOH has already considered the forthcoming data from new classes in the future rounds. Consequently, PLG-MOH can effectively adapt its hashing functions to address the new arriving samples and learn semantic similarity-preserved hash codes for them, meanwhile it can effectively retain the information learned from the old data. Extensive experiments on two public datasets demonstrate that the proposed PLG-MOH achieves better retrieval performance than state-of-the-art baselines on online scenarios. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Image Processing is the property of IEEE 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=191897226
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TIP.2025.3607626
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 5935
    Subjects:
      – SubjectFull: Hashing
        Type: general
      – SubjectFull: Electronic file management
        Type: general
      – SubjectFull: Message authentication codes
        Type: general
      – SubjectFull: Electronic data processing
        Type: general
      – SubjectFull: Information storage & retrieval systems
        Type: general
    Titles:
      – TitleFull: Prospective Layout-Guided Multi-Modal Online Hashing.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Tu, Rong-Cheng
      – PersonEntity:
          Name:
            NameFull: Mao, Xian-Ling
      – PersonEntity:
          Name:
            NameFull: Liu, Jin-Yu
      – PersonEntity:
          Name:
            NameFull: Ma, Zi-Ao
      – PersonEntity:
          Name:
            NameFull: Lan, Tian
      – PersonEntity:
          Name:
            NameFull: Huang, Heyan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 10577149
          Numbering:
            – Type: volume
              Value: 34
          Titles:
            – TitleFull: IEEE Transactions on Image Processing
              Type: main
ResultId 1