Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Network video event mining framework based on dynamic association rules

A network video and dynamic correlation technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of short, misleading, inaccurate titles and labels, and achieve the effect of reducing the impact

Inactive Publication Date: 2013-12-11
SOUTHWEST JIAOTONG UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, limited text information such as titles and tags usually use general, generalized, and vague words to roughly summarize the main content of the video, which contains more voices, inaccurate, and even misleading or wrong tags
These titles and tags are usually short, and a few words cannot cover the rich content of the video, which brings new challenges to network video event mining

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
  • Network video event mining framework based on dynamic association rules
  • Network video event mining framework based on dynamic association rules
  • Network video event mining framework based on dynamic association rules

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] This network video event mining framework is suitable for network videos uploaded by users with less text information and more noise. Now take m videos downloaded from the Internet as an example, recorded as V=1 ,V 2 ,V 3 …V m >, which contains a total of w words T=1 , T 2 , T 3 …T w >.

[0043] Data preprocessing. To reduce the impact of noise on text and visual parts, data preprocessing is an essential step. Video information, extracting visual approximation keyframes. For the video data set, in order to ensure the accuracy of similar key frame detection between videos, first, the Harris-Laplace method in the SIFT feature is used to extract local feature points. Secondly, the detection of similar keyframes is carried out through public tools, and a set of similar keyframes is obtained. Finally, using the correlation information between similar keyframe sets, they are further clustered through transitive closures to form "similar keyframe sets". Since the "si...

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 network video event mining framework based on dynamic association rules. Aiming at the characteristics of little information, much noise and the like of network video text information, by using semantic information among keywords and by dynamically adjusting the support degree in the association rules, influences on the relation between text and visual information caused by problems of noise, synonyms, polysemous words, multiple languages and the like are reduced, the robustness of text information is enhanced, and a bridge between visually approximate key frames and high-level semantics is established. The network video event mining framework based on dynamic association rules fully utilizes the semantic correlation among the text information and the relation between the text information and the visual information, the influences of noises in the text information on the relation between the visually approximate key frames and events are reduced, the correlation between the visually approximate key frames and the corresponding events is enhanced, and the framework is enabled to better adapt to event mining of network videos with much noise and little information.

Description

technical field [0001] The invention belongs to the field of data mining, and in particular relates to research on large-scale network video event mining in hot topic retrieval and tracking. Background technique [0002] The popularity of social networks has led to the explosive growth of online videos, and a key task when browsing massive online videos is event mining. With the development of multimedia technology, network technology and cable TV, video has become the main carrier for people to obtain information and enjoy entertainment in their daily life. By September 2009, roughly 20 hours of new video data was uploaded to YouTube every minute. YouTube accounts for about 10% of the entire internet traffic and 60% of the total online video volume. The Internet has become a center for publishing and sharing multimedia information, while Internet TV stations and "podcasts" have become important channels for obtaining multimedia information on the Internet. The explosive ...

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): G06F17/30
Inventor 吴晓张承德彭强
Owner SOUTHWEST JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com