标题:Supervised Hierarchical Cross-Modal Hashing
作者:Sun, Changchang; Song, Xuemeng; Feng, Fuli; Zhao, Wayne Xin; Zhang, Hao; Nie, Liqiang
通讯作者:Song, XM;Nie, LQ
作者机构:[Sun, Changchang; Song, Xuemeng; Nie, Liqiang] Shandong Univ, Jinan, Shandong, Peoples R China.; [Feng, Fuli] Natl Univ Singapore, Singapore, Singap 更多
会议名称:42nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
会议日期:JUL 21-25, 2019
来源:PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19)
出版年:2019
页码:725-734
DOI:10.1145/3331184.3331229
关键词:Cross-modal Retrieval; Layer-wise Hashing; Hierarchy
摘要:Recently, due to the unprecedented growth of multimedia data, cross-modal hashing has gained increasing attention for the efficient cross-media retrieval. Typically, existing methods on cross-modal hashing treat labels of one instance independently but overlook the correlations among labels. Indeed, in many real-world scenarios, like the online fashion domain, instances (items) are labeled with a set of categories correlated by certain hierarchy. In this paper, we propose a new end-to-end solution for supervised cross-modal hashing, named HiCHNet, which explicitly exploits the hierarchical labels of instances. In particular, by the pre-established label hierarchy, we comprehensively characterize each modality of the instance with a set of layer-wise hash representations. In essence, hash codes are encouraged to not only preserve the layer-wise semantic similarities encoded by the label hierarchy, but also retain the hierarchical discriminative capabilities. Due to the lack of benchmark datasets, apart from adapting the existing dataset FashionVC from fashion domain, we create a dataset from the online fashion platform Ssense consisting of 15, 696 image-text pairs labeled by 32 hierarchical categories. Extensive experiments on two real-world datasets demonstrate the superiority of our model over the state-of-the-art methods.
收录类别:CPCI-S;CPCI-SSH
资源类型:会议论文
TOP