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

Multimedia data identification method, apparatus and device, and computer storage medium

A technology for multimedia data and identification methods, applied in the field of data processing, can solve the problems of complex neural network model structure, slow identification speed, and large computational load of identification methods.

Active Publication Date: 2020-11-03
SOUNDAI TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the above-mentioned recognition method for multimedia data, the structure of the neural network model is relatively complicated, and the calculation amount is relatively large, which makes the calculation amount of the recognition method for multimedia data large and the recognition speed is relatively slow.

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
  • Multimedia data identification method, apparatus and device, and computer storage medium
  • Multimedia data identification method, apparatus and device, and computer storage medium
  • Multimedia data identification method, apparatus and device, and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0049] The neural network (Neural Networks) model is a model that simulates the actual neural network of humans. A neural network model includes at least one hidden layer. The Batch Normalization (BN) layer is connected to the hidden layer of the neural network model. The hidden layer The output of the BN layer is used as the input of the BN layer, and the output of the BN layer is used as the input of the next layer. The BN layer is a technology that can speed up the training speed of the neural network model and improve the output accuracy of the neural network model. The BN layer is added to the neural network model. The optimization of the neural network model can be realized.

[0050] When training a neural network model, ca...

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 multimedia data identification method, apparatus and device, and a computer storage medium, and belongs to the technical field of data processing. The method comprises the steps of: obtaining a second neural network model; acquiring multimedia data to be identified; and recognizing the multimedia data to be recognized through the second neural network model and obtaininga recognition result. Since the second neural network model does not include the target batch standardization layer, the same function of the target batch standardization layer is realized by the batch standardization processing formula determined according to the preprocessing parameters of the target batch standardization layer, so that the structure of the second neural network model can be simplified; and the calculation amount of batch standardization processing in the second neural network model is reduced, and the processing speed of the neural network model is increased. According to the invention, the problems of large calculation amount and low recognition speed of the multimedia data recognition method in the related art are solved, and the effects of reducing the calculation amount of the multimedia data recognition method and increasing the recognition speed are achieved.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a multimedia data identification method, device, equipment and computer storage medium. Background technique [0002] Multimedia data recognition is a technology for recognizing various multimedia data such as image data and audio data. Through the recognition of image data and audio data, various technologies such as classification, processing and analysis of image data and audio data can be realized. Effect. [0003] In a method for identifying multimedia data in the related art, the multimedia data to be identified is identified through a neural network model, the neural network model includes at least one hidden layer, and a batch normalization (Batch Normalization, BN) layer is connected to the neural network model. After the hidden layer, the output of the hidden layer is used as the input of the BN layer, and the output of the BN layer is used as the inp...

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): G06N3/04G06N3/08G06F17/16
CPCG06N3/08G06F17/16G06N3/045
Inventor 栾天祥陈孝良冯大航
Owner SOUNDAI TECH CO LTD