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

A video description method and device

A video description and video technology, applied in the field of video processing, can solve problems such as loss of information, inaccurate description, and reduced utility, and achieve the effects of strong robustness, improved efficiency and accuracy, and improved index and search quality

Active Publication Date: 2022-05-13
GUILIN UNIV OF ELECTRONIC TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if a video is improperly tagged, its utility is greatly reduced
The existing method for describing video is to extract some frames intermittently for description, this method will lose some information, making the description inaccurate, and the retrieval of the video cannot be accurate

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
  • A video description method and device
  • A video description method and device
  • A video description method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0017] figure 1 It is a schematic flowchart of a video description method provided by an embodiment of the present invention.

[0018] like figure 1 and 2 As shown, a video description method includes the following steps:

[0019] Importing the video to be tested, performing temporal semantic feature segmentation on the video to be tested, and obtaining multiple shot data;

[0020] Converting and analyzing each of the lens data through a preset video description model to obtain lens description information corresponding to each of the lens data;

[0021] Sentence fusion analysis is performed on the plurality of shot description information to obtain video description information.

[0022] It should be understoo...

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 present invention provides a video description method and device. The method includes: importing a video to be tested, performing temporal semantic feature segmentation on the video to be tested to obtain multiple shot data; performing conversion analysis to obtain shot description information corresponding to each of the shot data; performing sentence fusion analysis on multiple shot description information to obtain video description information. The invention can ensure that the information in the video is not lost, and does not generate semantic redundancy of shots, can describe each shot, helps to improve the index and search quality of online videos, and improves the efficiency and efficiency of video retrieval. accuracy, greater robustness, and the potential to benefit the visually impaired.

Description

technical field [0001] The present invention mainly relates to the technical field of video processing, and in particular to a video description method and device. Background technique [0002] The video description task poses an important challenge for computer vision and machine learning research, and it has various practical applications, for example, 100 hours of videos are uploaded to YouTube every minute. However, if a video is improperly labeled, its utility is greatly reduced. The prior art method for describing video is to extract some frames intermittently for description. This method will lose some information, making the description inaccurate, and the retrieval of the video will also be inaccurate. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a video description method and device for the deficiencies of the prior art. [0004] The technical solution of the present invention to solve the above-me...

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 Patents(China)
IPC IPC(8): G06V20/40G06V10/74G06V10/82G06F16/71G06F16/783G06K9/62G06N3/04
CPCG06F16/71G06F16/783G06V20/46G06V20/49G06N3/044G06F18/22
Inventor 蔡晓东王湘晴
Owner GUILIN UNIV OF ELECTRONIC TECH