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

Cross-media hash retrieval method and device, terminal and storage medium

A cross-media and hash technology, applied in the field of hash retrieval, can solve the problem of low accuracy of cross-media hash retrieval, achieve the effect of maintaining pairwise similarity, improving accuracy, and enhancing expression ability

Active Publication Date: 2022-01-21
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned defects of the prior art, the present invention provides a cross-media hash retrieval method, device, terminal and storage medium, aiming to solve the problem of low accuracy of cross-media hash retrieval in the prior art

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
  • Cross-media hash retrieval method and device, terminal and storage medium
  • Cross-media hash retrieval method and device, terminal and storage medium
  • Cross-media hash retrieval method and device, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 Shown, in an embodiment of described cross-media hash retrieval method, comprise steps:

[0059] S100. Select at least one sample data group from the sample data set to obtain a target training batch.

[0060] The sample data set includes a plurality of sample data groups, and each sample data group includes a sample label vector, first sample data, and second sample data corresponding to the sample data group. The data type of the first sample data is a first media type, and the type of the second sample data is a second media type. Media data with different media formats are referred to as data with different media types, and the media types may be text, image, video, audio, and so on. For cross-media retrieval, it is necessary to convert data objects with similar semantics for different media types into similar hash codes, so as to realize similarity retrieval. In this embodiment, for data of different media types, different hash learning networks...

Embodiment 2

[0149] Based on the above embodiments, the present invention also provides a corresponding cross-media hash retrieval device, such as Figure 4 As shown, the cross-media hash retrieval device includes:

[0150] A training batch determination module, the training batch determination module is used to select at least one sample data group in the sample data set to obtain a target training batch, wherein the sample data set includes a plurality of sample data groups, each sample data The group includes the sample label vector corresponding to the sample data group, the first sample data and the second sample data, the data type of the first sample data is the first media type, and the type of the second sample data is the second Media type, specifically as described in Embodiment 1;

[0151] A feature hash module, the hash module is used to determine the sample hash feature corresponding to the target sample data group in the target training batch, the sample hash feature corres...

Embodiment 3

[0157] Based on the above embodiments, the present invention also provides a corresponding terminal, such as Figure 5 As shown, the terminal includes a processor 10 and a memory 20 . Figure 5 Only some components of the terminal are shown, but it should be understood that implementation of all illustrated components is not required, and more or fewer components may be implemented instead.

[0158] The storage 20 may be an internal storage unit of the terminal in some embodiments, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD ) card, flash memory card (Flash Card), etc. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various...

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

The invention discloses a cross-media hash retrieval method and device, a terminal and a storage medium, and the method comprises the steps of selecting at least one sample data set from a sample data set, and obtaining a target training batch; determining a sample hash feature corresponding to the target sample data set; determining a prediction label vector corresponding to the target sample data group; obtaining tag hash features corresponding to the target sample data set according to the sample tag vector corresponding to the target sample data set; determining training loss according to the sample hash feature, the tag hash feature, the sample tag vector and the predicted tag vector, and updating parameters of the first feature hash learning network and the second feature hash learning network according to the training loss; and determining a hash code of the data of the first media type by using the first feature hash learning network after parameter convergence, and determining a hash code of the data of the second media type by using the second feature hash learning network after parameter convergence. According to the invention, the accuracy of cross-media hash retrieval can be improved.

Description

technical field [0001] The invention relates to the technical field of hash retrieval, in particular to a cross-media hash retrieval method, device, terminal and storage medium. Background technique [0002] Similarity search as a basis for machine learning, computer vision, and multimedia. In recent years, the huge and explosive growth of multimedia data has greatly increased the urgent need to develop complex similarity search systems for multimedia data. What is particularly noteworthy in this requirement is that data is always collected from different sources, and formed in different forms, represented by different media data, resulting in large-scale, heterogeneous multimedia data. Therefore, how to achieve fast cross-media similarity measurement and accurate retrieval has become a hot issue in the current multimedia field. [0003] However, currently proposed hash learning-based cross-media retrieval methods that support similarity retrieval across different media ar...

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): G06F16/41G06F16/45G06F16/901G06F16/906
CPCG06F16/41G06F16/45G06F16/9014G06F16/906
Inventor 张正罗浩洋卢光明
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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