Unlock instant, AI-driven research and patent intelligence for your innovation.

An unsupervised cross-modal retrieval model training method based on deep dual variational hashing

A model training and cross-modal technology, applied in the field of cross-modal retrieval, can solve the problems of not being able to effectively use the correlation of different modal data, and not being able to obtain high-precision retrieval results

Active Publication Date: 2021-04-16
合肥综合性国家科学中心人工智能研究院
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In cross-modal retrieval, different modal data of the same target play a complementary role, but the current hashing method cannot effectively utilize the correlation between different modal data, resulting in the inability to obtain high-precision retrieval results

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
  • An unsupervised cross-modal retrieval model training method based on deep dual variational hashing
  • An unsupervised cross-modal retrieval model training method based on deep dual variational hashing
  • An unsupervised cross-modal retrieval model training method based on deep dual variational hashing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0070] In order to better understand the above-mentioned technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0071] It should be noted that, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of element...

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 model training method based on image retrieval text, a cross-modal retrieval model training method based on text retrieval image, and an unsupervised cross-modal retrieval model training method based on deep dual variational hashing . The technical problem of low accuracy of cross-modal retrieval is solved, and the accuracy of cross-modal retrieval is improved.

Description

technical field [0001] The present invention relates to the technical field of cross-modal retrieval, in particular to a cross-modal retrieval model training method based on image retrieval text, a cross-modal retrieval model training method based on text retrieval image, and a wireless retrieval method based on deep dual variational hashing. A Supervised Cross-Modal Retrieval Model Training Approach. Background technique [0002] With the rapid development of information technology, multimedia data such as images and texts in search engines and social networks has exploded. The increase in the amount of multimedia data also increases the difficulty of multimedia data retrieval. How to accurately retrieve the required results from massive multimedia data is a key research topic in the current retrieval field. [0003] Cross-modal retrieval refers to the retrieval technology of retrieving data of another modality through data of one modality. Common cross-modal retrieval m...

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): G06K9/62G06N3/04G06N3/08G06F40/30G06F16/43
CPCG06F16/43G06F40/30G06N3/08G06N3/045G06F18/22G06F18/214
Inventor 张勇东李攀登谢洪涛
Owner 合肥综合性国家科学中心人工智能研究院