Discrete Multi-graph Hashing for Large-Scale Visual Search

认领

导出

下载 Link by 万方学术期刊

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Xiang, Lingyun;Shen, Xiaobo*;Qin, Jiaohua;Hao, Wei

通讯作者：

Shen, Xiaobo

作者机构：

[Xiang, Lingyun] Changsha Univ Sci & Technol, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha 410114, Hunan, Peoples R China.

[Xiang, Lingyun] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Hunan, Peoples R China.

[Xiang, Lingyun] Changsha Univ Sci & Technol, Hunan Prov Key Lab Smart Roadway & Cooperat Vehic, Changsha 410114, Hunan, Peoples R China.

[Shen, Xiaobo] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Jiangsu, Peoples R China.

[Qin, Jiaohua] Cent South Univ Forestry & Technol, Coll Comp Sci & Informat Technol, Changsha 410004, Hunan, Peoples R China.

通讯机构：

[Shen, Xiaobo] N

Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Jiangsu, Peoples R China.

语种：

英文

关键词：

Artificial intelligence;Software engineering;Alternative algorithms;Comprehensive information;Hashing;Multi-graph;Multi-view datum;Optimization algorithms;Optimization problems;Retrieval;Optimization

期刊：

Neural Processing Letters

ISSN：

1370-4621

年：

2019

卷：

期：

页码：

1055-1069

DOI：

10.1007/s11063-018-9892-7

基金类别：

Acknowledgements This project is supported by National Natural Science Foundation of China (Nos. 61202439 and 61772561), and partly supported by Scientific Research Fundation of Hunan Provincial Education Department of China (No. 16A008) and Hunan Provincial Key Laboratory of Smart Roadway and Cooperative Vehicle-Infrastructure Systems (No. 2017TP1016).

机构署名：

本校为其他机构

院系归属：

计算机与信息工程学院

摘要：

Hashing has become a promising technique to be applied to the large-scale visual retrieval tasks. Multi-view data has multiple views, providing more comprehensive information. The challenges of using hashing to handle multi-view data lie in two aspects: (1) How to integrate multiple views effectively? (2) How to reduce the distortion error in the quantization stage? In this paper, we propose a novel hashing method, called discrete multi-graph hashing (DMGH), to address the above challenges. DMGH uses a multi-graph learning technique to fuse mul...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Discrete Multi-graph Hashing for Large-Scale Visual Search

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问