版权说明 操作指南
首页 > 成果 > 详情

Multi-Label Weighted Contrastive Cross-Modal Hashing

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Yi, Zeqian;Zhu, Xinghui;Wu, Runbing;Zou, Zhuoyang;Liu, Yi;...
通讯作者:
Zhu, L
作者机构:
[Zhu, Lei; Zhu, L; Zhu, Xinghui; Liu, Yi; Yi, Zeqian; Zou, Zhuoyang; Wu, Runbing] Hunan Agr Univ, Coll Informat & Intelligence, Changsha 410128, Peoples R China.
通讯机构:
[Zhu, L ] H
Hunan Agr Univ, Coll Informat & Intelligence, Changsha 410128, Peoples R China.
语种:
英文
关键词:
cross-modal hashing;contrastive learning;multi-label;compact consistent similarity;similarity weight assigning
期刊:
Applied Sciences-Basel
ISSN:
2076-3417
年:
2024
卷:
14
期:
1
页码:
93-
基金类别:
Conceptualization, L.Z.; methodology, Z.Y. and L.Z.; software, Z.Y.; validation, Z.Y., R.W. and Z.Z.; formal analysis, L.Z.; investigation, X.Z. and Z.Y.; resources, X.Z. and L.Z.; data curation, R.W. and Z.Z.; writing—original draft preparation, Z.Y.; writing—review and editing, L.Z. and Y.L.; visualization, R.W. and Z.Z.; supervision, X.Z. and L.Z.; project administration, X.Z.; funding acquisition, X.Z. and L.Z. All authors have read and agreed to the published version of the manuscript. This work was supported in part by the National Natural Science Foundation of China (62202163, 62072166), the Natural Science Foundation of Hunan Province (2022JJ40190), the Scientific Research Project of Hunan Provincial Department of Education (22A0145), and the Key Research and Development Program of Hunan Province (2020NK2033).
机构署名:
本校为第一且通讯机构
摘要:
Due to the low storage cost and high computation efficiency of hashing, cross-modal hashing has been attracting widespread attention in recent years. In this paper, we investigate how supervised cross-modal hashing (CMH) benefits from multi-label and contrastive learning (CL) by overcoming the following two challenges: (i) how to combine multi-label and supervised contrastive learning to consider diverse relationships among cross-modal instances, and (ii) how to reduce the sparsity of multi-label representation so as to improve the similarity measurement accuracy. To this end, we propose a nov...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com