Fast Partial-Modal Online Cross-Modal Hashing.
Saved in:
| Title: | Fast Partial-Modal Online Cross-Modal Hashing. |
|---|---|
| Authors: | Li, Fengling1, Sun, Yang2 young7869264s@gmail.com, Wang, Tianshi2, Zhu, Lei3, Chang, Xiaojun1 |
| Source: | IEEE Transactions on Image Processing. 2025, Vol. 34, p4440-4455. 16p. |
| Subjects: | Hashing, Electronic file management, Message authentication codes, Image compression, Digital image processing |
| Abstract: | Cross-Modal Hashing (CMH) has become a powerful technique for large-scale cross-modal retrieval, offering benefits like fast computation and efficient storage. However, most CMH models struggle to adapt to streaming multimodal data in real-time once deployed. Although recent online CMH studies have made progress in this area, they often overlook two key challenges: 1) learning effectively from streaming partial-modal multimodal data, and 2) avoiding the high costs associated with frequent hash function re-training and large-scale updates to database hash codes. To address these issues, we propose Fast Partial-modal Online Cross-Modal Hashing (FPO-CMH), the first approach to tackle online cross-modal hash learning with partial-modal data. This marks a significant shift from previous methods that rely on fully-available multimodal data. Specifically, our approach introduces a multimodal dual-tier anchor bank, initialized using offline training data, which allows offline-trained CMH models to adapt seamlessly to partial-modal data while progressively updating the anchor bank. By leveraging gradient accumulation and asynchronous optimization, FPO-CMH facilitates efficient online cross-modal hash learning. Additionally, an initial-anchor rehearsal strategy is employed to prevent model catastrophic forgetting during online optimization, ensuring the code invariance of database hash codes and eliminating the need for frequent hash function re-training. Extensive experiments validate the superiority of FPO-CMH, especially in handling streaming partial-modal multimodal data, a more realistic scenario. The source codes and datasets are available at https://github.com/DandelionWow/FPO-CMH [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: 191897137 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Fast Partial-Modal Online Cross-Modal Hashing. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Li%2C+Fengling%22">Li, Fengling</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Sun%2C+Yang%22">Sun, Yang</searchLink><relatesTo>2</relatesTo><i> young7869264s@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Tianshi%22">Wang, Tianshi</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Lei%22">Zhu, Lei</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Chang%2C+Xiaojun%22">Chang, Xiaojun</searchLink><relatesTo>1</relatesTo> – 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, p4440-4455. 16p. – 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="%22Image+compression%22">Image compression</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+image+processing%22">Digital image processing</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Cross-Modal Hashing (CMH) has become a powerful technique for large-scale cross-modal retrieval, offering benefits like fast computation and efficient storage. However, most CMH models struggle to adapt to streaming multimodal data in real-time once deployed. Although recent online CMH studies have made progress in this area, they often overlook two key challenges: 1) learning effectively from streaming partial-modal multimodal data, and 2) avoiding the high costs associated with frequent hash function re-training and large-scale updates to database hash codes. To address these issues, we propose Fast Partial-modal Online Cross-Modal Hashing (FPO-CMH), the first approach to tackle online cross-modal hash learning with partial-modal data. This marks a significant shift from previous methods that rely on fully-available multimodal data. Specifically, our approach introduces a multimodal dual-tier anchor bank, initialized using offline training data, which allows offline-trained CMH models to adapt seamlessly to partial-modal data while progressively updating the anchor bank. By leveraging gradient accumulation and asynchronous optimization, FPO-CMH facilitates efficient online cross-modal hash learning. Additionally, an initial-anchor rehearsal strategy is employed to prevent model catastrophic forgetting during online optimization, ensuring the code invariance of database hash codes and eliminating the need for frequent hash function re-training. Extensive experiments validate the superiority of FPO-CMH, especially in handling streaming partial-modal multimodal data, a more realistic scenario. The source codes and datasets are available at https://github.com/DandelionWow/FPO-CMH [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=191897137 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TIP.2025.3586504 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 4440 Subjects: – SubjectFull: Hashing Type: general – SubjectFull: Electronic file management Type: general – SubjectFull: Message authentication codes Type: general – SubjectFull: Image compression Type: general – SubjectFull: Digital image processing Type: general Titles: – TitleFull: Fast Partial-Modal Online Cross-Modal Hashing. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Li, Fengling – PersonEntity: Name: NameFull: Sun, Yang – PersonEntity: Name: NameFull: Wang, Tianshi – PersonEntity: Name: NameFull: Zhu, Lei – PersonEntity: Name: NameFull: Chang, Xiaojun 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 |
