Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Visual questioning and answering method based on mathematical chart data set

A data set and chart technology, applied in the field of visual question answering, to achieve the effect of improving the accuracy

Inactive Publication Date: 2020-01-07
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention proposes a visual question answering method based on a data set of mathematical charts, which solves the existing five types of visual question answering problems of mathematical charts

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
  • Visual questioning and answering method based on mathematical chart data set
  • Visual questioning and answering method based on mathematical chart data set
  • Visual questioning and answering method based on mathematical chart data set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] 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.

[0031] refer to Figure 1-4 , a visual question answering method based on a mathematical graph class dataset, including the following steps:

[0032] S1, the target detection based on the Faster-RCNN model, the target detection based on the Faster-RCNN model includes two stages of detection objects: the area candidate frame of the target proposed by the area candidate network, on the output of the convolutional feature map of the final shared convolutional layer Sliding a small network, each sliding window predicts k region proposals at the same time, and performs non-maximum value suppression on candidate frames with an intersection ratio greater than a certain thre...

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 relates to the technical field of visual questions and answers, discloses a visual questioning and answering method based on a mathematical chart data set, and provides the following scheme for existing five types of mathematical chart visual questions and answers: S1, performing target detection based on a Faster-RCNN model; wherein the model is used for identifying object instancesbelonging to certain classes and determining the position of the object in the image through a bounding box; s2, performing object feature coding based on a target detection result; s3, preprocessingthe question-answer pair; s4, performing the text question feature extraction; and S5, performing visual intelligent questioning and answering based on a relation reasoning module, in S1, target detection based on a Faster-RCNN model comprises two stages of detection objects. The invention provides a solution combining a target detection module and an inference module, which is used for solving the visual question-answering problem of five types of mathematical charts, and improves the accuracy.

Description

technical field [0001] The invention relates to the technical field of visual question answering, in particular to a visual question answering method based on a mathematical diagram data set. Background technique [0002] Visual question answering is a novel problem domain. The visual question answering system needs to process the image and natural language input provided by the task, and combine the reasoning process to obtain accurate natural language answers. [0003] At present, most visual question answering systems are implemented based on datasets that mirror real scenes, but there are few studies on visual question answering based on mathematical graph datasets; the model proposed by Revanth Reddy is currently unable to solve the problem of line graphs. Contents of the invention [0004] The present invention proposes a visual question answering method based on a data set of mathematical graphs, which solves the existing five types of visual question answering prob...

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 Applications(China)
IPC IPC(8): G06F16/9032G06F16/908G06N3/04G06N3/08
CPCG06F16/90332G06F16/908G06N3/08G06N3/045
Inventor 张迪雅周尔强杨航银正强曹黛
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
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