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

A Discrete Hash Retrieval Method for Cross-Modal Data Based on Similarity Preservation

A similarity and cross-modal technology, applied in discrete hash retrieval of cross-modal data, cross-modal retrieval field, can solve problems affecting retrieval performance

Active Publication Date: 2021-04-13
ZHEJIANG UNIV +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this relaxation strategy can affect the retrieval performance

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 Discrete Hash Retrieval Method for Cross-Modal Data Based on Similarity Preservation
  • A Discrete Hash Retrieval Method for Cross-Modal Data Based on Similarity Preservation
  • A Discrete Hash Retrieval Method for Cross-Modal Data Based on Similarity Preservation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0054] Such as figure 1 Shown, the specific embodiment of the present invention situation is as follows:

[0055] The specific implementation is to further illustrate the technical scheme of the present invention with a flow chart and a cross-modal data set Wiki; wherein, the cross-modal data set Wiki is derived from Wikipedia, and includes 2866 image-text pairs collected from Wikipedia articles . Images are represented by 128-dimensional SIFT features, and texts are represented by 10-dimensional LDA features. The image-text pairs in the Wiki dataset are divided into 10 semantic categories, and each image-text pair belongs to one of these categories. 2173 samples are randomly selected to form the training set, and the remaining 693 samples form the test set.

[0056] 1) In the database of the server, a cross-modal retrieval data s...

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 discrete hash retrieval method for cross-modal data based on similarity preservation. Establish a cross-modal retrieval data set composed of samples containing two modalities, which is divided into training set and test set; establish an objective function that maintains inter-modal similarity and intra-modal similarity, and uses a discrete optimization method to Solve the objective function to obtain the hash code matrix; learn the hash function of each mode according to the hash code matrix; use the hash function to calculate the hash code of all samples in the training set and test set; a modal test set is the query set, Another modal training set is the retrieval set, which calculates the Hamming distance between the hash codes of the samples in the query set and the hash codes of the samples in the retrieval set, and ranks them as the retrieval results. The present invention can effectively maintain the similarity between modals and the similarity within a modal, and consider the discrete characteristics of the hash code, and adopt a discrete optimization method to solve the objective function, thereby improving the efficiency of cross-modal retrieval accuracy.

Description

technical field [0001] The invention relates to a cross-modal retrieval method in the technical field of multimedia retrieval, in particular to a discrete hash retrieval method for cross-modal data based on similarity preservation. Background technique [0002] With the rapid development of Internet information technology, multimedia information in various modes on the network is growing explosively. Following the development trend, cross-modal retrieval has become a crucial issue and has attracted the attention of many researchers. A typical scenario of cross-modal retrieval is to retrieve a query sample of a modality and retrieve other modalities similar to it. However, due to the heterogeneity gap, it is impossible to directly measure the similarity between different modalities. In addition, due to the explosive growth of data, it is necessary to pay attention to the storage cost and efficiency of large-scale retrieval. The hash method is a very popular method in recen...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/41G06F16/43G06F16/483
Inventor 孔祥维李明阳
Owner ZHEJIANG UNIV
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