Cross-Modal Hashing via Diverse Instances Matching.
Saved in:
| Title: | Cross-Modal Hashing via Diverse Instances Matching. |
|---|---|
| Authors: | Tu, Junfeng1 ganlantee@gmail.com, Liu, Xueliang1 liuxueliang1982@gmail.com, Huang, Zhen2 huangzhen@nudt.edu.cn, Hao, Yanbin1 haoyanbin@hotmail.com, Hong, Richang1 hongrc.hfut@gmail.com, Wang, Meng1 eric.mengwang@gmail.com |
| Source: | IEEE Transactions on Image Processing. 2025, Vol. 34, p2737-2749. 13p. |
| Subjects: | Hashing, Estimation theory, Information retrieval, Electronic file management, Semantics, Labels |
| Abstract: | Cross-modal hashing is a highly effective technique for searching relevant data across different modalities, owing to its low storage costs and fast similarity retrieval capability. While significant progress has been achieved in this area, prior investigations predominantly concentrate on a one-to-one feature alignment approach, where a singular feature is derived for similarity retrieval. However, the singular feature in these methods fails to adequately capture the varied multi-instance information inherent in the original data across disparate modalities. Consequently, the conventional one-to-one methodology is plagued by a semantic mismatch issue, as the rigid one-to-one alignment inhibits effective multi-instance matching. To address this issue, we propose a novel Diverse Instances Matching for Cross-modal Hashing (DIMCH), which explores the relevance between multiple instances in different modalities using a multi-instance learning algorithm. Specifically, we design a novel diverse instances learning module to extract a multi-feature set, which enables our model to capture detailed multi-instance semantics. To evaluate the similarity between two multi-feature sets, we adopt the smooth chamfer distance function, which enables our model to incorporate the conventional similarity retrieval structure. Moreover, to sufficiently exploit the supervised information from the semantic label, we adopt the weight cosine triplet loss as the objective function, which incorporates the multilevel similarity among the multi-labels into the training procedure and enables the model to mine the multi-label correlation effectively. Extensive experiments demonstrate that our diverse hashing embedding method achieves state-of-the-art performance in supervised cross-modal hashing retrieval tasks. [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: 191897016 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Cross-Modal Hashing via Diverse Instances Matching. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tu%2C+Junfeng%22">Tu, Junfeng</searchLink><relatesTo>1</relatesTo><i> ganlantee@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Xueliang%22">Liu, Xueliang</searchLink><relatesTo>1</relatesTo><i> liuxueliang1982@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Huang%2C+Zhen%22">Huang, Zhen</searchLink><relatesTo>2</relatesTo><i> huangzhen@nudt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Hao%2C+Yanbin%22">Hao, Yanbin</searchLink><relatesTo>1</relatesTo><i> haoyanbin@hotmail.com</i><br /><searchLink fieldCode="AR" term="%22Hong%2C+Richang%22">Hong, Richang</searchLink><relatesTo>1</relatesTo><i> hongrc.hfut@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Meng%22">Wang, Meng</searchLink><relatesTo>1</relatesTo><i> eric.mengwang@gmail.com</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, p2737-2749. 13p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Hashing%22">Hashing</searchLink><br /><searchLink fieldCode="DE" term="%22Estimation+theory%22">Estimation theory</searchLink><br /><searchLink fieldCode="DE" term="%22Information+retrieval%22">Information retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+file+management%22">Electronic file management</searchLink><br /><searchLink fieldCode="DE" term="%22Semantics%22">Semantics</searchLink><br /><searchLink fieldCode="DE" term="%22Labels%22">Labels</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Cross-modal hashing is a highly effective technique for searching relevant data across different modalities, owing to its low storage costs and fast similarity retrieval capability. While significant progress has been achieved in this area, prior investigations predominantly concentrate on a one-to-one feature alignment approach, where a singular feature is derived for similarity retrieval. However, the singular feature in these methods fails to adequately capture the varied multi-instance information inherent in the original data across disparate modalities. Consequently, the conventional one-to-one methodology is plagued by a semantic mismatch issue, as the rigid one-to-one alignment inhibits effective multi-instance matching. To address this issue, we propose a novel Diverse Instances Matching for Cross-modal Hashing (DIMCH), which explores the relevance between multiple instances in different modalities using a multi-instance learning algorithm. Specifically, we design a novel diverse instances learning module to extract a multi-feature set, which enables our model to capture detailed multi-instance semantics. To evaluate the similarity between two multi-feature sets, we adopt the smooth chamfer distance function, which enables our model to incorporate the conventional similarity retrieval structure. Moreover, to sufficiently exploit the supervised information from the semantic label, we adopt the weight cosine triplet loss as the objective function, which incorporates the multilevel similarity among the multi-labels into the training procedure and enables the model to mine the multi-label correlation effectively. Extensive experiments demonstrate that our diverse hashing embedding method achieves state-of-the-art performance in supervised cross-modal hashing retrieval tasks. [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=191897016 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TIP.2025.3561659 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 2737 Subjects: – SubjectFull: Hashing Type: general – SubjectFull: Estimation theory Type: general – SubjectFull: Information retrieval Type: general – SubjectFull: Electronic file management Type: general – SubjectFull: Semantics Type: general – SubjectFull: Labels Type: general Titles: – TitleFull: Cross-Modal Hashing via Diverse Instances Matching. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tu, Junfeng – PersonEntity: Name: NameFull: Liu, Xueliang – PersonEntity: Name: NameFull: Huang, Zhen – PersonEntity: Name: NameFull: Hao, Yanbin – PersonEntity: Name: NameFull: Hong, Richang – PersonEntity: Name: NameFull: Wang, Meng 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 |
