OPT OpenIR  > 光谱成像技术研究室
Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features
Lu, Xiaoqiang1,2; Chen, Yaxiong1,2; Li, Xuelong1,2
作者部门光学影像学习与分析中心
2018
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
卷号27期号:1页码:106-120
产权排序1
摘要

Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.

文章类型Article
关键词Image Retrieval Supervised Hashing Hierarchical Convolutional Features Hierarchical Rnn
WOS标题词Science & Technology ; Technology
DOI10.1109/TIP.2017.2755766
收录类别SCI ; EI
关键词[WOS]CODES ; DEEP
语种英语
WOS研究方向Computer Science ; Engineering
项目资助者National Natural Science Foundation of China(61761130079 ; Key Research Program of Frontier Sciences, CAS(QYZDY-SSW-JSC044) ; Chinese Academy of Sciences(QYZDB-SSW-JSC015) ; 61472413 ; 61772510)
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000413256300008
EI入藏号20174104260201
引用统计
被引频次:101[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/29374
专题光谱成像技术研究室
作者单位1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Beijing 100049, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714
Lu, Xiaoqiang,Chen, Yaxiong,Li, Xuelong. Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(1):106-120.
APA Lu, Xiaoqiang,Chen, Yaxiong,&Li, Xuelong.(2018).Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(1),106-120.
MLA Lu, Xiaoqiang,et al."Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.1(2018):106-120.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Hierarchical Recurre(2781KB)期刊论文出版稿限制开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Lu, Xiaoqiang]的文章
[Chen, Yaxiong]的文章
[Li, Xuelong]的文章
百度学术
百度学术中相似的文章
[Lu, Xiaoqiang]的文章
[Chen, Yaxiong]的文章
[Li, Xuelong]的文章
必应学术
必应学术中相似的文章
[Lu, Xiaoqiang]的文章
[Chen, Yaxiong]的文章
[Li, Xuelong]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。