Cross-modal retrieval method based on collaborative matrix decomposition

A matrix decomposition and cross-modal technology, applied in the field of image processing, can solve the problems of low retrieval effect and long retrieval time, and achieve the effect of improving the accuracy of mutual retrieval, maintaining similarity, and guaranteeing similarity.

Active Publication Date: 2018-07-27
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, these methods have certain limitations, the retrieval effect is relatively low, and the retrieval time

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-modal retrieval method based on collaborative matrix decomposition
  • Cross-modal retrieval method based on collaborative matrix decomposition
  • Cross-modal retrieval method based on collaborative matrix decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0045] In the era of big data, the acquisition and processing of information is very important, and retrieval technology is the key step. Especially in the case of a large number of various modal data, how to carry out effective information retrieval is the focus of relevant scholars, and it is also the focus of related work. However, the existing cross-modal retrieval methods have the disadvantages of slow retrieval speed and low accuracy of retrieval of relevant information.

[0046] In view of this problem, the present invention launched innovative research, and proposed a cross-modal retrieval method based on collaborative matrix decomposition, see figure 1 , the whole retrieval process includes the following steps:

[0047] Step 1, to obtain the original data, first perform feature extraction on the image and text in the original data (wherei...

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-modal retrieval method based on collaborative matrix decomposition. Keeping local geometric manifold structure for an original spatial sample pair is considered; intramodal and intermodal restraints are added via graphic regular items; mAP (mean average precision) that is commonly used is used as a performance evaluation index. The intramodal similarity of samples is considered, and the intermodal similarity of the sample pair is also considered; accuracy in text-based graph retrieval and graph-based retrieval is guaranteed. The collaborative matrix decomposition technique and hash function are utilized, graphic regular items to keep intramodal and intermodal similarity are added, mutual retrieving performance is improved for text-based graph retrieval and graph-based retrieval, and the method is widely applicable to image-text mutual retrieval services in mobile devices, the internet and e-commerce.

Description

technical field [0001] The invention relates to a cross-modal retrieval method based on collaborative matrix decomposition, in particular to a graph regularization method considering maintaining intra-modal similarity and inter-modal similarity of original spatial data, and belongs to the technical field of image processing. Background technique [0002] With the rapid development of Internet technology, society has entered the era of big data. Big data is expressed in different modalities such as images, texts, audio, and video. These different modalities of data are not independent, and they have an essential connection. How to mine the correlation information between data has become a hot spot of attention. [0003] As a basic related technology, cross-modal retrieval technology is widely used in the fields of machine learning, computer vision and data mining, such as retrieving images with text and retrieving text with images. However, big data has a series of character...

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): G06F17/30
CPCG06F16/325G06F16/3331G06F16/5846
Inventor 李新卫荆晓远吴飞孙莹
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap