[1]滕少华,郭兰君,张 巍,等.一种标签嵌入子空间的跨模态离散哈希学习[J].江西师范大学学报(自然科学版),2021,(03):305-313.[doi:10.16357/j.cnki.issn1000-5862.2021.03.13]
　TENG Shaohua,GUO Lanjun,ZHANG Wei,et al.The Cross-Modal Discrete Hash Learning of Tag Embedding Subspace[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(03):305-313.[doi:10.16357/j.cnki.issn1000-5862.2021.03.13]
点击复制

一种标签嵌入子空间的跨模态离散哈希学习()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年03期
页码:
305-313
栏目:
信息科学与技术
出版日期:
2021-06-10

文章信息/Info

Title:
The Cross-Modal Discrete Hash Learning of Tag Embedding Subspace
文章编号:
1000-5862(2021)03-0305-09
作者:
滕少华1; 郭兰君1; 张 巍1; 滕璐瑶2
1.广东工业大学计算机学院,广东 广州 510006; 2.维多利亚大学应用信息研究中心,维多利亚 墨尔本 3011
Author(s):
TENG Shaohua1; GUO Lanjun1; ZHANG Wei1; TENG Luyao2
1.School of Computers,Guangdong University of Technology,Guangzhou Guamgdong 510006,China; 2.The Centre for Applied Informatics,Victoria University,Melbourne Victoria 3011,Australia
关键词:
标签嵌入;  子空间;  离散哈希
Keywords:
tag embedding;  subspace;  discrete hash
分类号:
TP 391
DOI:
10.16357/j.cnki.issn1000-5862.2021.03.13
文献标志码:
A
摘要:
针对有监督的跨模态哈希检索存在计算成本高及准确度不高的问题,提出了一种标签嵌入子空间的跨模态离散哈希学习方法,将数据信息和标签信息同时嵌入到公共子空间中,通过以带标签信息的语义特征逼近公共子空间、并生成低松弛的离散哈希码,降低了计算成本,快速生成了具有丰富语义的公共子空间.经3个标准数据集对比实验,结果表明其准确率均优于被比较的方法.
Abstract:
Because supervised cross-modal hash retrieval has still problems of high computational cost and low accuracy of retrieval,a cross-modal discrete hash learning method for tag embedding subspace is proposed,which embeds data information and tag information into the common subspace at the same time.The common subspace is approximated by semantic features with tag information,and discrete hash codes with low slack are generated,which greatly reduces the computational cost and quickly generates a common subspace with rich semantics.This method is compared with 3 standard data sets,and the results show that the retrieval accuracy is better than the compared method.

参考文献/References:

[1] 彭宇新,綦金玮,黄鑫,等.Current research status and prospects on Multimedia content understanding[J].计算机研究与发展,2019,56(1):183-208.
[2] Fei Wu,Zhou Yu,Yang Yi,et al.Sparse multi-modal mashing[J].IEEE Transactions on Multimedia,2014,16(2):427-439.
[3] Song Jingkuan,Yang Yang,Yang Yi,et al.Inter-media hashing for large-scale retrieval from heterogeneous data sources[EB/OL].[2020-06-15].https://doi.org/10.1145/2463676.2465274.
[4] Long Mingsheng,Cao Yue,Wang Jianmin,et al.Composite correlation quantization for efficient multimodal retrieval[EB/OL].[2020-06-12].https://doi.org/10.1145/2911451.2911493.
[5] Liu Hong,Ji Rongrong,Wu Yongjian,et al.Cross-modality binary code learning via fusion similarity hashing[EB/OL].[2020-06-18].10.1109/CVPR.2017.672.
[6] Zhou Jile,Ding Guiguang,Guo Yuchen,et al.Latent semantic sparse hashing for cross-modal similarity search[EB/OL].[2020-06-19].https://dl.acm.org/doi/10.1145/2600428.2609610.
[7] Ding Guiguang,Guo Yuchen,Zhou Jile,et al.Collective matrix factorization hashing for multi-modal data[EB/OL].[2020-06-19].https://doi.org/10.1109/CVPR.2014.267.
[8] Fei Wu,Zhou Yu,Yang Yang,et al.Sparse multi-modal hashing[EB/OL].[2020-06-19].https://ieeexplore.ieee.org/document/6665155.
[9] Bronstein M,Bronstein A M,Michel F,et al.Data fusion through cross-modality metric learning using similarity-sensitive hashing[EB/OL].[2020-05-19].https://ieeexplore.ieee.org/document/5539928.
[10] Lin Zijia,Ding Guiguang,Hu Mingqing,et al.Semantics-preserving hash-ing for cross-view retrieval[EB/OL].[2020-05-13].https://ieeexplore.ieee.org/document/7299011?arnumber=7299011.
[11] Zhang Dongqing,Li Wujun.Large-scale supervised multimodal hash-ing with semantic correlation maximization[EB/OL].[2020-05-09].https://cs.nju.edu.cn/lwj/paper/AAAI14_SCM.pdf.
[12] Kan Meina,Shan Shiguang,Zhang Haihong,et a1.Multi-view discriminant analysis[EB/OL].[2020-06-19].https://dl.acm.org/doi/10.1007/978-3-642-33718-5_58.
[13] Wang Kaiyue,He Ran,Wang Wei,et al.Learning coupled feature spaces for cross-modal matching[EB/OL].[2020-06-19].https://dl.acm.org/doi/10.1109/ICCV.2013.261.
[14] 费伦科,秦建阳,滕少华,等.近似最近邻大数据检索哈希散列方法综述[J].广东工业大学学报,2020,37(3):10-22.
[15] Gong Yunchao,Ke Qifa,ISARD M,et al.A multi-view embedding space for modeling internet images,tags,and their semantics[J].International Journal of Computer Vision,2014,106(2):210-233.
[16] Ranjan V,Rasiwasia N,Jawahar C V.Multi-label cross-modal retrieval[EB/OL].[2020-05-11].https://ieeexplore.ieee.org/document/7410823.
[17] Zhou Jile,Ding Guiguang,Guo Yuchen.Latent semantic sparse hashing for cross-modal similarity search[EB/OL].[2020-05-12].https://dblp.org/rec/conf/sigir/ZhouDG14.html.
[18] Fei Wu,Zhou Yu,Yang Yang,et al.Sparse multi-modal hashing[J].IEEE Trans Multimedia,2014,16(2):427-439.
[19] Wang Di,Gao Xinbo,Wang Xiumei,et al.Semantic topic multi-modal hashing for cross-media retrieval[EB/OL].[2020-05-12].https://dl.acm.org/doi/10.5555/2832747.2832791.
[20] Rasiwasia N,Pereira J C,Coviello E,et al.A new approach to cross-modal multi-media retrieval[EB/OL].[2020-05-17].https://dl.acm.org/doi/10.1145/1873951.1873987.
[21] Liu Wei,Mu Cun,Kumar S,et al.Discrete graph hashing[EB/OL].[2020-07-19].https://dl.acm.org/doi/10.1.1.673.2750.
[22] Chua T S,Tang Jinhui,Hong Richang,et al.NUS-WIDE:a real-world web image database from national university of Singapore[EB/OL].[2020-05-10].https://dl.acm.org/doi/10.1145/1646396.1646452.
[23] Huiskes M J,Lew M S.The MIRflickr retrieval evaluation[EB/OL].[2020-05-14].https://dl.acm.org/doi/10.1145/1460096.1460104.
[24] Liu Hong,Ji Rongrong,Wu Yongjian,et al.Supervised matrix factorization for cross modality hashing[EB/OL].[2020-05-14].https://dl.acm.org/doi/10.5555/3060832.3060868.
[25] Xu Xing,Shen Fumin,Yang Yang,et al.Learning discriminative binary codes for large-scale cross-modal retrieval[EB/OL].[2020-05-16].https://dl.acm.org/doi/10.1109/TIP.2017.2676345.
[26] Liu Hong,Ji Rongrong,Wu Yongjian,et al.Cross-modality binary code learning via fusion similarity hashing[EB/OL].[2020-05-10].https://ieeexplore.ieee.org/document/8100155/citations#citations.
[27] Chen Zhenduo,Li Chuanxiang,Luo Xin,et al.SCRATCH:a scalable discrete matrix factorization hashing framework for cross-modal retrieval[EB/OL].[2020-05-19].https://dl.acm.org/doi/10.1109/TCSVT.2019.2911359.

备注/Memo

备注/Memo:
收稿日期:2020-10-17
基金项目:广东省重点领域研发计划(2020B010166006),国家自然科学基金(61972102)和广州市科技计划(201903010107,201802030011,201802010026,201802010042,201604046017)资助项目.
作者简介:滕少华(1962—),男,江西南昌人,教授,博士,主要从事大数据、数据挖掘、数字音频分析与处理、网络安全方面的研究.E-mail:shteng@gdut.edu.cn
更新日期/Last Update: 2021-06-10