Visual question-answering method based on structured semantic representation

A semantic representation and structuring technology, applied in the field of computer vision, can solve problems such as ignoring semantic structure information, achieve the effect of enriching feature dimensions, improving accuracy, and improving performance

Pending Publication Date: 2020-04-14
SHANGHAI JIAO TONG UNIV
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this chain structure ignores the semantic structure information in the text

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 question-answering method based on structured semantic representation
  • Visual question-answering method based on structured semantic representation
  • Visual question-answering method based on structured semantic representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0042] figure 1 It is a schematic diagram of the principle of the visual question answering model of the present invention, such as figure 1 As shown in Fig. 1, the convolutional neural network is first used to extract image features. In order to maintain the position information of the image, the output of the pooling layer is usually selected as the image feature. Using the trained word embedding model, the word vector of each word is obtained. Then, the Tree-LSTM network is used to extract the stru...

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 provides a visual question-answering method based on structured semantic representation. The visual question-answering method comprises the following steps: extracting image features ofan input image through a convolutional neural network; extracting a word vector of each word from an input problem related to the input image through a pre-trained character embedding model; performing weighting processing on the image feature and the word vector to obtain weighted image feature vectors and text feature vectors; converting the word vector into a structured semantic representationvector through a Tree-LSTM network; performing fusion processing on the image feature vector, the text feature vector and the structured semantic representation vector to obtain a corresponding fusionfeature vector; and taking the fusion feature vector as the input of a prediction model, and outputting an answer corresponding to the input question by the prediction model. According to the method,richer semantic information is extracted from the question, and the performance of the prediction model is improved through multi-layer training optimization so that the accuracy of answers is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a visual question answering method based on structured semantic representation. Background technique [0002] In the field of computer vision, visual question answering is a very cutting-edge and challenging problem. Given a natural image, any question can be asked about the content of the image. In order to be able to accurately predict questions, it is necessary to be able to fully obtain data information during the modeling process of visual question answering, and to represent it in a more robust representation. The training method of the visual question answering model itself is also very important, and it is necessary to accurately find the boundary of the classifier. Due to the compositional structure of language itself, different questions often have similar substructures, which also means that the reasoning process in visual question answering must be compositi...

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): G06F16/583G06F16/58G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/424G06N3/045G06F18/253
Inventor 熊红凯余东晨
Owner SHANGHAI JIAO TONG UNIV
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