标题:Fast discrete cross-modal hashing with regressing from semantic labels
作者:Liu, Xingbo ;Cui, Chaoran ;Nie, Xiushan ;Zhu, Lei ;Zeng, Wenjun ;Yin, Yilong
通讯作者:Yin, Yilong
作者机构:[Liu, Xingbo ] School of Computer Science and Technology, Shandong University, China;[Zhu, Lei ] School of Information Science and Engineering, Shando 更多
会议名称:26th ACM Multimedia conference, MM 2018
会议日期:22 October 2018 through 26 October 2018
来源:MM 2018 - Proceedings of the 2018 ACM Multimedia Conference
出版年:2018
页码:1662-1669
DOI:10.1145/3240508.3240683
关键词:Cross-modal retrieval; Learning-based hashing; Supervised hashing
摘要:Hashing has recently received great attention in cross-modal retrieval. Cross-modal retrieval aims at retrieving information across heterogeneous modalities {e.g., texts vs. images). Cross-modal hashing compresses heterogeneous high-dimensional data into compact binary codes with similarity preserving, which provides efficiency and facility in both retrieval and storage. In this study, we propose a novel fast discrete cross-modal hashing (FDCH) method with regressing from semantic labels to take advantage of supervised labels to improve retrieval performance. In contrast to existing methods that learn the projection from hash codes to semantic labels, the proposed FDCH regresses the semantic labels of training examples to the corresponding hash codes with a drift. It not only accelerates the hash learning process, but also helps generate stable hash codes. Furthermore, the drift can adjust the regression and enhance the discriminative capability of hash codes. Especially in the case of training efficiency, FDCH is much faster than existing methods. Comparisons with several state-of-the-art techniques on three benchmark datasets have demonstrated the superiority of FDCH under various cross-modal retrieval scenarios. © 2018 Association for Computing Machinery.
收录类别:EI;SCOPUS
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85058232543&doi=10.1145%2f3240508.3240683&partnerID=40&md5=924ab84143339fb776c09ae990806cda
TOP