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

Cross-modal retrieval algorithm based on mixed hypergraph learning in subspace

A subspace learning and cross-modal technology, applied in the computer field, can solve problems such as ignoring the high-order relationship of samples

Active Publication Date: 2017-06-23
DALIAN UNIV OF TECH
View PDF3 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, no matter the method based on cross-modal hashing or the method of subspace learning, most of them only consider the relationship between two pairs when measuring the relationship between samples, and ignore the high-level relationship between more samples. order relationship

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 algorithm based on mixed hypergraph learning in subspace
  • Cross-modal retrieval algorithm based on mixed hypergraph learning in subspace
  • Cross-modal retrieval algorithm based on mixed hypergraph learning in subspace

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The specific implementation manners of the present invention will be further described below in conjunction with the drawings and technical solutions.

[0023] figure 1 It is a flowchart of the cross-modal retrieval algorithm based on subspace hybrid hypergraph learning. In the present invention, two modes of text and pictures are used as cross-modal retrieval samples. Firstly, feature extraction needs to be performed on different modalities. For text data, Latent Dirichlet Distribution (LDA) is used for feature extraction. For image modalities, convolutional neural network (CNN) is used for feature learning. After obtaining the respective feature representations of the two modalities, the next step is to use canonical correlation analysis for common subspace learning, mapping the original image and text modalities to the same dimensional space, so that the similarity between them can be directly measured , to eliminate heterogeneous differences between different mod...

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 algorithm based on mixed hypergraph learning in subspace, based on the cross-modal public subspace learning of canonical correlation analysis. The similarities inside and among modals are calculated by a mapping of the public subspace. A mixed relation matrix is calculated by the similarities inside and among the modals. A mixed hypergraph model is built by the extraction of the relation matrix. And the cross-modal retrieval and sample sequencing are conducted by adoption of hypergraph learning finally. With aiming at cross-modal heterogeneous variations and high order relation among samples, the algorithm instance applies the hypergraph model combined with the cross-modal public subspace learning to the cross-modal retrieval, so that the model is capable of considering the similarity among the modals and the similarity inside the modals simultaneously and giving consideration to the high order relation among a plurality of the samples meanwhile, improving the final precision ratio and the final recall ratio of the cross-modal retrieval. The algorithm is capable of effectively improving the performance of the cross-modal retrieval and greatly enhancing the precision ratio and the recall ratio of the cross-modal retrieval.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a cross-modal retrieval algorithm based on subspace hybrid hypergraph learning. Background technique [0002] At present, the problem of multimodal retrieval has attracted the attention of a large number of scholars. Due to the existence of a large amount of multimedia data in the Internet, such as images, texts, videos, etc., a variety of expressions are provided for the semantic description of an object. For example, a cat description may include: a description of a cat, a recorded video of a cat, a recording of a cat meowing, or some pictures of a cat. The multi-modal retrieval problem is aimed at the cross-retrieval between multiple modalities, that is, using images to retrieve related texts, or using texts to retrieve related images. For retrieval between two modalities, it is called cross-modal retrieval. However, due to the inherent heterogeneity of differ...

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
CPCG06F16/43
Inventor 陈志奎钟芳明钟华鲁飞
Owner DALIAN UNIV OF TECH
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