Cross-modal search system

A search system and cross-modal technology, applied in the field of cross-modal search, can solve problems such as single modality, limited query data and search result data, and achieve the effect of improving semantic understanding and solving the inability to directly retrieve each other.

Pending Publication Date: 2022-01-18
深圳前海黑顿科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional single-modal search system can no longer meet the growing needs of users, because its query data and search result data are limited to a single modality

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 search system
  • Cross-modal search system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention belong to the protection scope of the present invention.

[0032] According to an embodiment of the present invention, a cross-modal search system is provided.

[0033] Such as Figure 1-Figure 2 As shown, the cross-modal search system according to the embodiment of the present invention includes:

[0034] Cross-modal retrieval module 1, resource library generation module 2 and quantification library 3, wherein;

[0035] The cross-modal retrieval module 1 is used to obtain user-input retrieval features and encoding results and store information as ...

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 search system, which relates to the technical field of cross-modal search. The cross-modal search system comprises a cross-modal retrieval module, a resource library generation module and a quantization library, wherein the cross-modal retrieval module is used for serving as information input to obtain retrieval features and coding results input by a user, storing the information and determining corresponding high-dimensional vectors; the resource library generation module is used for establishing a corrected resource and a quantized code thereof and storing the corrected resource and the quantized code thereof into a specified modal region of a quantized library so as to provide support for retrieval operation; and the quantification library is used for storing all the to-be-retrieved resources. Fusion and supplement of various modal information are realized, semantic understanding of the information during cross-modal search can be effectively improved, the problem that resources of different modals cannot be directly and mutually retrieved is solved, and the resources can be converted into a uniform and normative computable quantification form.

Description

technical field [0001] The present invention relates to the technical field of cross-modal search, in particular to a cross-modal search system. Background technique [0002] In recent years, the development of artificial intelligence has made great breakthroughs, so that artificial intelligence has been deeply applied in many fields. Deep learning technology in artificial intelligence has developed rapidly in recent years, especially in the field of natural language processing. With the continuous development of deep learning, for some tasks, the ability of deep learning models to complete tasks has exceeded human beings. Modality refers to the existence form of data, such as text, audio, image, video and other file formats. Some data exist in different forms, but they all describe the same thing or event, and data of different modalities are often required for information retrieval. To enrich our cognition of the same thing or event, cross-modal search is used to realize...

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): G06F16/9032G06F16/901G06K9/62G06F17/16G06N3/04
CPCG06F16/90324G06F16/901G06F17/16G06N3/045G06F18/22
Inventor 裴正奇于秋鑫朱斌斌段必超
Owner 深圳前海黑顿科技有限公司
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