Online Fast Adaptive Low-Rank Similarity Learning for Cross-Modal Retrieval

doi:10.1109/TMM.2019.2942494

	Online Fast Adaptive Low-Rank Similarity Learning for Cross-Modal Retrieval
	Wu, Yiling 1; Wang, Shuhui 1; Huang, Qingming 1,2
	2020-05-01
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	22 期号:5 页码:1310-1322
摘要	The semantic similarity among cross-modal data objects, e.g., similarities between images and texts, are recognized as the bottleneck of cross-modal retrieval. However, existing batch-style correlation learning methods suffer from prohibitive time complexity and extra memory consumption in handling large-scale high dimensional cross-modal data. In this paper, we propose a Cross-Modal Online Low-Rank Similarity function learning (CMOLRS) method, which learns a low-rank bilinear similarity measurement for cross-modal retrieval. We model the cross-modal relations by relative similarities on the training data triplets and formulate the relative relations as convex hinge loss. By adapting the margin in hinge loss with pair-wise distances in feature space and label space, CMOLRS effectively captures the multi-level semantic correlation and adapts to the content divergence among cross-modal data. Imposed with a low-rank constraint, the similarity function is trained by online learning in the manifold of low-rank matrices. The low-rank constraint not only endows the model learning process with faster speed and better scalability, but also improves the model generality. We further propose fast-CMOLRS combining multiple triplets for each query instead of standard process using single triplet at each model update step, which further reduces the times of gradient updates and retractions. Extensive experiments are conducted on four public datasets, and comparisons with state-of-the-art methods show the effectiveness and efficiency of our approach.
关键词	Semantics Correlation Training Data models Visualization Adaptation models Fasteners Cross-modality learning similarity function learning online learning low-rank matrix
DOI	10.1109/TMM.2019.2942494
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61672497] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61836002] ; National Basic Research Program of China under 973 Program[2015CB351802] ; Key Research Program of Frontier Sciences of CAS[QYZDJ-SSW-SYS013]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000530097200016
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/15385
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Shuhui
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Wu, Yiling,Wang, Shuhui,Huang, Qingming. Online Fast Adaptive Low-Rank Similarity Learning for Cross-Modal Retrieval[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2020,22(5):1310-1322.
APA	Wu, Yiling,Wang, Shuhui,&Huang, Qingming.(2020).Online Fast Adaptive Low-Rank Similarity Learning for Cross-Modal Retrieval.IEEE TRANSACTIONS ON MULTIMEDIA,22(5),1310-1322.
MLA	Wu, Yiling,et al."Online Fast Adaptive Low-Rank Similarity Learning for Cross-Modal Retrieval".IEEE TRANSACTIONS ON MULTIMEDIA 22.5(2020):1310-1322.