
The Library
DAP2CMH : deep adversarial privacy-preserving cross-modal hashing
Tools
Zhu, Lei, Song, Jiayu, Yang, Zhan, Huang, Wenti, Zhang, Chengyuan and Yu, Weiren (2021) DAP2CMH : deep adversarial privacy-preserving cross-modal hashing. Neural Processing Letters . doi:10.1007/s11063-021-10447-4 (In Press)
Research output not available from this repository, contact author.
Official URL: http://dx.doi.org/10.1007/s11063-021-10447-4
Abstract
Privacy-preserving cross-modal retrieval is a significant problem in the area of multimedia analysis. As the amount of data is exploding, cross-modal data analysis and retrieval is often realized on cloud computing environment. Therefore, the privacy protection of large-scale cross-modal data has become a problem that can not be ignored. To further improve the accuracy and efficiency of privacy-preserving search, this paper proposes a novel cross-modal hashing scheme, named deep adversarial privacy-preserving cross-modal hashing (DAP2CMH). This method consists of a deep cross-modal hashing model termed DACMH, and a secure index structure called CMH2-Tree. The former is a combination of deep hashing and adversarial learning to capture intra-modal and inter-modal correlation. The latter is a hierarchical hashing index structure that can provide efficient data organization based on cross-modal hash codes. We conduct comprehensive experiments on three common used benchmarks. The results show that the proposed approach DAP2CMH outperforms the state-of-the-arts.
Item Type: | Journal Article | ||||||
---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science > Computer Science | ||||||
Journal or Publication Title: | Neural Processing Letters | ||||||
Publisher: | Springer New York LLC | ||||||
ISSN: | 1370-4621 | ||||||
Official Date: | 7 March 2021 | ||||||
Dates: |
|
||||||
DOI: | 10.1007/s11063-021-10447-4 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | In Press | ||||||
Access rights to Published version: | Restricted or Subscription Access |
Request changes or add full text files to a record
Repository staff actions (login required)
![]() |
View Item |