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

Method for constructing voice-assisted audio-visual collaborative learning new target network model

A network model and construction method technology, applied in the field of computer vision, can solve problems such as new target network models that do not have new targets for online learning, audio-visual collaborative learning, etc., and achieve the effect of strong generalization ability

Inactive Publication Date: 2020-04-28
SOUTHWEST JIAOTONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned deficiencies of the prior art, the present invention provides a method for constructing a new target network model for voice-assisted audio-visual collaborative learning that solves the defect that the existing network model does not have a new target for online learning

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
  • Method for constructing voice-assisted audio-visual collaborative learning new target network model
  • Method for constructing voice-assisted audio-visual collaborative learning new target network model
  • Method for constructing voice-assisted audio-visual collaborative learning new target network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0045] Such as figure 1 As shown, the construction method of the new target network model of voice-assisted audio-visual collaborative learning includes the following steps:

[0046] S1: Build an original object classifier M1 for identifying the original object and an object feature extraction model M2 for extracting the feature vector of the object;

[0047] The method for building the original object classifier M1 for or...

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 method for constructing a voice-assisted audio-visual collaborative learning new target network model. The method comprises the steps of S1-S11, the method is based on a traditional object recognition model and an image feature matching technology. The known object is accurately recognized through the initial object recognition model, if a new object appears, feature memory is conducted on the new object through the online learning model, and the initial object recognition model is updated in real time, so that the generalization ability of the model is higher, and the method is more suitable for application in a real scene.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for constructing a new target network model for voice-assisted audio-visual collaborative learning. Background technique [0002] With the rapid development of computer vision, object recognition technology has been applied to various fields, and has brought huge economic benefits. In recent years, many object recognition network models have emerged, and their recognition accuracy has been continuously improved, but they have a common defect, that is, image data sets must be prepared in advance, trained for existing data sets, and an object is generated. Detector. In practical applications, there are many types of objects, and many image data cannot be collected or are difficult to obtain. In some scenarios, it is not known in advance which categories of image data should be prepared, which makes it difficult to apply traditional network models to actual scenar...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V10/757G06V10/462G06N3/045G06F18/24
Inventor 苟先太康立烨钱照国张葛祥
Owner SOUTHWEST JIAOTONG UNIV