Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A similarity-retaining cross-modal hash retrieval method

A similarity and cross-modality technology, applied in the field of similarity-preserving cross-modal hash retrieval, which can solve the problems of insufficient reduction of redundant information in hash coding and insufficient similarity preservation.

Active Publication Date: 2019-01-25
JIUJIANG UNIVERSITY
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a similarity-preserving cross-modal hash retrieval method, which solves the problem that many existing methods do not fully preserve the similarity of samples within and between modalities, and that each The problem of insufficient reduction of redundant information on the bit makes the learned hash code have good discrimination ability

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A similarity-retaining cross-modal hash retrieval method
  • A similarity-retaining cross-modal hash retrieval method
  • A similarity-retaining cross-modal hash retrieval method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] A similarity-preserving cross-modal hash retrieval approach, assuming n objects The features in image modal and text modal are respectively and Among them, d 1 and d 2 denote the dimensions of image modality and text modality feature vectors, respectively, and Represent the characteristics of the i-th object in the image mode and text mode respectively; at the same time, it is assumed that the feature vectors of the image mode and text mode are preprocessed by zero centralization, that is, satisfy Assume that the label matrix formed by the category labels of n objects is L=[l 1 , l 2 ,...,l n ]∈{0,1} l×n , where l i (i=1,2,...,n) represents the category label information of the i-th object, l is the number of categories; suppose the cross-modal similarity matrix is ​​S∈{0,1} n×n , where S ij Indicates the similarity between the i-th sample in the image modality and the j-th sample in the text modality; if the i-th sample in the image modality is similar...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A similarity-retaining cross-modal hash retrieval method comprises the following steps: (1) constructing an objective function based on a similarity retaining strategy; (2) solving the objective function; (3) generating a sample binary hash codes in a query sample and a retrieval sample set; (4) calculating Hamming distances between the query sample and each sample in the retrieval sample set; (5)using a cross-modal retriever to complete the retrieval of the query sample. The method of the invention can not only fully retain the similarity of samples between modes, but also retain the similarity of samples in the modes when carrying out hash learning, so that the Hamming space obtained by learning has stronger identification ability and is more conducive to completing cross-modal retrieval.

Description

technical field [0001] The invention relates to a similarity preserving cross-modal hash retrieval method. Background technique [0002] In all walks of life in today's society, a large number of users have accumulated massive amounts of user data (for example, the search engine Chrome has more than 100PB of data), and the amount of data is still growing exponentially, and the era of big data is coming. Big data plays a very important role in Internet finance, medical care, education, military and transportation industries. For example, combining big data with machine learning technology can provide reliable basis for financial investment and market decision-making. Today's big data has the following characteristics: (1) large volume, the data volume is in PB; (2) high dimensionality, data features have thousands of dimensions; (3) many modes, many types of data, and various forms , including images, text, audio and video. These characteristics of big data have brought ser...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/33
Inventor 董西伟杨茂保孙丽董小刚尧时茂王玉伟邓安远邓长寿
Owner JIUJIANG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com