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

Method for acquiring hotspot video information based on video tags

A technology of video labeling and hotspot information, which is applied in the fields of instruments, computing, and electronic digital data processing, etc., can solve the problems of inaccurate advertising push, poor delivery effect, irrelevant advertising content and video content, etc., and achieve accurate description of hotspot features, Improve delivery performance

Inactive Publication Date: 2012-07-11
HUAZHONG UNIV OF SCI & TECH
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing video tagging technologies are all for describing the entire video, and cannot describe the highlights of the video
In addition, the existing video tagging technology still has inaccurate descriptions, resulting in inaccurate advertisement push based on the existing video tagging technology, irrelevant advertising content and video content, and poor delivery effect

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 acquiring hotspot video information based on video tags
  • Method for acquiring hotspot video information based on video tags
  • Method for acquiring hotspot video information based on video tags

Examples

Experimental program
Comparison scheme
Effect test

example

[0031] Assuming that the content of the video tag in the current video is "Jordan's dunk from the free throw line is so cool!", through semantic segmentation, we can get "Jordan", "this", "free throw line", "jump", "of", "slam dunk" ", "very handsome" words, get the words "Jordan", "free throw line", and "slam dunk" through part-of-speech filtering, and calculate the TF-IDF value of the two words, assuming the TF-IDF value of "Jordan" here is 0.4, the TF-IDF value of "free throw line" is 0.45, and the TF-IDF value of "slam dunk" is 0.3. After sorting, three features of "free throw line", "Jordan" and "slam dunk" are obtained descriptor. Count the number of tags at each time point in the entire video, take the k time points with the most tags (the value of k is equal to the quotient of video length divided by 3), define these k time points as temporary hotspots, and divide each temporary hotspot The feature descriptors of the first and last 10 seconds are merged into the tempo...

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 acquiring hotspot video information based on video tags, which comprises the following steps of: acquiring a video tag of a video, wherein the video tag comprises time points and tag contents of the video; carrying out Chinese word segmentation on the tag contents of the video tag; filtering the obtained word segmentation results so as to keep nouns and verbs as feature description words of a time point at which the video tag is located; calculating the importance degree values of the feature description words in the video tag; according to the importance degree values, carrying out sequencing on the feature description words, and taking the most important k feature description words as standby hotspot words of the time point; and carrying out statistical modeling on the standby hotspot words so as to generate hotspot video information. By using the method disclosed by the invention, the accuracy of video description can be improved through hotspots, thus the hotspot-based advertisement delivery effect is improved.

Description

technical field [0001] The invention relates to the field of network video applications, and more specifically, the invention relates to a method for acquiring video hotspot information based on video tags. Background technique [0002] Video tags are phrases used to describe the characteristics of a video. Existing video labeling technologies are all for describing the whole video, and cannot describe the highlights of the video. In addition, the existing video tagging technology still has inaccurate descriptions, resulting in inaccurate advertising push based on the existing video tagging technology, irrelevant advertising content and video content, and poor delivery effects. Contents of the invention [0003] In view of this, the purpose of the present invention is to provide a method for obtaining video hotspot information based on video tags, which can improve the accuracy of video description through hotspots, and then improve the effect of advertising push based on...

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): G06F17/30
Inventor 金海廖小飞陆枫曲鑫
Owner HUAZHONG UNIV OF SCI & TECH
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