中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Online Fast Adaptive Low-Rank Similarity Learning for Cross-Modal Retrieval

文献类型：期刊论文

作者Wu, Yiling1; Wang, Shuhui1; Huang, Qingming1,2
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2020-05-01
卷号22期号:5页码:1310-1322
关键词Semantics Correlation Training Data models Visualization Adaptation models Fasteners Cross-modality learning similarity function learning online learning low-rank matrix
ISSN号1520-9210
DOI10.1109/TMM.2019.2942494
英文摘要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.
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
语种英语
WOS记录号WOS:000530097200016
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/15384]  
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。