检索结果-内蒙古大学图书馆

Ensemble learning framework for image retrieval via deep hash ranking

KNOWLEDGE-BASED SYSTEMS 2023年 260卷

作者： Li, Donggen Dai, Dawei Chen, Jiancu Xia, Shuyin Wang, Guoyin Chongqing Univ Telecommun & Posts Coll Chongqing Key Lab Computat Intelligence Chongqing Peoples R China Chongqing Three Gorges Univ Key Lab Intelligent Informat Proc & Control Chongqing Peoples R China

Deep hashing combines feature extraction or representation with hash coding jointly, which can significantly improve the speed of large-scale image retrieval. However, we notice that compared with traditional retrieval methods, due to the reduction of dimension and information loss, the retrieval performance of binaryhash coding has declined to a certain extent. Most hash retrieval algorithms focus on the semantic similarity between image pairs, and ignore the ranking information between the returned samples. The returned samples should not only match the retrieved samples, but also rank the correct samples in front of the returned list. In addition, the performance difference of the deep model used in deep hash retrieval will also limit the efficiency of retrieval. To address such problem, we proposed an ensemble deep neural model robust framework for image retrieval, which can learn compact hash codes containing rich semantic information through hash constraints. The ensemble strategy is introduced, and the weighted voting is applied to integrate the ranking list. Comprehensive experiments on three benchmark datasets show that the proposed method achieves very competitive results. Codes are available at https://***/lidonggen-123/Ensemble_Deephash_Image_Retrieval.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Image retrieval hash coding Ensemble learning Convolutional neural network Transformer

来源：评论

学校读者我要写书评

暂无评论

Generating a Rotation Reduction Perfect hashing Function

引用

Mathematics Magazine 1995年第1期68卷 35-41页

作者： Arlene Blasius

Click to increase image sizeClick to decrease image size

关键词： hash coding Identifiers Mathematical functions Integers Mathematical sets Information retrieval Mathematical theorems Remainders

来源：评论

学校读者我要写书评

暂无评论

A Study of Trie-Like Structures Under the Density Model

引用

The Annals of Applied Probability 1992年第2期2卷 402-434页

作者： Luc Devroye

We consider random tries constructed from sequences of i.i.d. random variables with a common density $f$ on $\lbrack 0, 1 \rbrack$ (i.e., paths down the tree are carved out by the bits in the binary expansions of the random variables). The depth of insertion of a node and the height of a node are studied with respect to their limit laws and their weak and strong convergence properties. In addition, laws of the iterated logarithm are obtained for the height of a random trie when $\int f^2 < \infty$. Finally, we study two popular improvements of the trie, the $\mathrm{PATRICIA}$ tree and the digital search tree, and show to what extent they improve over the trie.

关键词： Random variables Integers Entropy hash coding Data models Plant roots Algorithms Logarithms Leaves Information search

来源：评论

学校读者我要写书评

暂无评论

Assigning Driver's License Numbers

引用

Mathematics Magazine 1991年第1期64卷 13-22页

作者： Joseph A. Gallian

Click to increase image sizeClick to decrease image size

关键词： Birth Drivers licenses Term weighting Numbers Family names International standard book numbers Middle names Given names hash coding

来源：评论

学校读者我要写书评

暂无评论

DETECTION OF COMBINED OCCURRENCES

引用

COMMUNICATIONS OF THE ACM 1977年第1期20卷 31-35页

作者： ZOBRIST, AL CARLSON, FR UNIV SO CALIF LOS ANGELESCA 90007 UNIV ARIZONA TUCSONAZ 85721

Examines the detection of combined occurrences for a large number of changes of values of variables. Description of the two efficient solutions for the combined occurrences; Properties of the methods; Error analysis f... 详细信息

关键词： artificial intelligence chess coding demons hash coding n-tuples pattern recognition retrieval secondary keys sorting

来源：评论

学校读者我要写书评

暂无评论

KEY-TO-ADDRESS TRANSFORM TECHNIQUES - FUNDAMENTAL PERFORMANCE STUDY ON LARGE EXISTING FORMATTED FILES

引用

COMMUNICATIONS OF THE ACM 1971年第4期14卷 228-&页

作者： LUM, VY YUEN, PST DODD, M IBM Research Lab. San Jose CA IBM Research Lab. San Jose CA IBM Research Lab. San Jose CA

Studies key-to-address transformation methods applied to a set of existing files. Correlation between the number of accesses required to get to a record and the number of overflows record created by a transformation; Techniques of accessing a single record of a formatted file; Guidelines for the selection of an appropriate practical transform.

关键词： cluster collisions direct access method direct addressing file addressing file organizations file structures hash coding hashing hashing methods hashing techniques information retrieval key transformation key-to-address transformation keys random access randomizing scatter storage search

来源：评论

学校读者我要写书评

暂无评论

COMMENTS ON PERFECT hashING FUNCTIONS - SINGLE PROBE RETRIEVING METHOD FOR STATIC SETS

引用

COMMUNICATIONS OF THE ACM 1979年第2期22卷 104-104页

作者： ANDERSON, MR ANDERSON, MG COMSHARE INC ANN ARBORMI 48104

The article presents a study which discussed perfect hashing functions in computer science. The author said that possible difficulties in implementing Algorithm T may be avoided. The symbol \ indicates set difference. The value of d which is output in step (g) of Algorithm R corresponds only to the final rotation value discovered by Algorithm T, the rest having already been output by step (j) of T. It is more effective to modify step (j) of T to determine d if only one remainder reduction phf is desired.

关键词： direct addressing hash coding hashing hashing methods identifier-to-address transformations perfect hash coding perfect hashing functions reduction retrieving scatter storage searching

来源：评论

学校读者我要写书评

暂无评论

MINIMAL PERFECT hash FUNCTIONS MADE SIMPLE

引用

COMMUNICATIONS OF THE ACM 1980年第1期23卷 17-19页

作者： CICHELLI, RJ Software Consulting Services Allentown PA

Presents a method for computing machine independent in minimal perfect hash functions. Application of compilers in filtering high frequency words in natural language processing; Presentation of examples on English wor... 详细信息

关键词： Pascal Pascal reserved words backtracking dictionary lookup direct addressing hash coding hashing hashing methods indentifier-to-address transformations information retrieval lexical analysis perfect hash coding perfect hashing functions scatter storage searching

来源：评论

学校读者我要写书评

暂无评论

ADDITIONAL RESULTS ON KEY-TO-ADDRESS TRANSFORM TECHNIQUES - FUNDAMENTAL PERFORMANCE STUDY ON LARGE EXISTING FORMATTED FILES

引用

COMMUNICATIONS OF THE ACM 1972年第11期15卷 996-&页

作者： LUM, VY YUEN, PST IBM Research Lab. San Jose CA IBM Research Lab. San Jose CA

The article provides an analysis of key-to-address transformation techniques and the results of a performance study on large existing formatted files. The experimental results comparing six commonly used key-to-address transformation techniques were presented by the researchers. One transformation in the study referred to as 'generalized radix transformation method' is an elaborate technique based on radix transformation. This method of transformation consists of a radix transformation algorithm as well as hardware implementation to carry out the steps of this transformation in an efficient manner. The intricacy of the generalized radix transformation method has motivated researchers to conduct further studies of the technique. The additional results are presented after a brief description of the basic algorithm used in this generalized radix transformation method. Additional experiments on the files showed that the distribution of the keys was particularly sensitive to the arbitrary selection of an 8-bit grouping.

关键词： direct access method direct addressing file organization file search hash coding hashing hashing methods hashing techniques information retrieval key transformation key-to-address transformation keys random access randomizing scatter storage

来源：评论

学校读者我要写书评

暂无评论

GENERAL PERFORMANCE ANALYSIS OF KEY-TO-ADDRESS TRANSFORMATION METHODS USING AN ABSTRACT FILE CONCEPT

引用

COMMUNICATIONS OF THE ACM 1973年第10期16卷 603-612页

作者： LUM, VY IBM CORP RES LABMONTEREY & COTTLE RDSAN JOSECA 95193

This paper presents a new approach to the analysis of performance of the various key-to-address transformation methods. In this approach the keys in a file arc assumed to have been selected from the key space according to a certain probabilistic selection algorithm. All files with the same number of keys selected from this key space will be suitably weighted in accordance with the algorithm, and the average performance of the transformation methods on these files will be used as the potential of these methods. Using this analysis, methods with the same overall performance can be classified and key distributions partial to certain transformations can be identified. All this can be done analytically. The approach is applied to a group of transformation methods using files whose keys are selected randomly. [ABSTRACT FROM AUTHOR]

关键词： direct addressing hash coding hashing hashing analysis hashing methods hashing techniques information retrieval key transformation key-to-address transformation random access randomization performance analysis randomizing scatter storage

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：