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

Method and apparatus for content representation and retrieval in concept model space

A model, conceptual technology, applied in the field of indexing multimedia documents

Inactive Publication Date: 2006-03-15
INT BUSINESS MASCH CORP
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Auto-tagging technology can be used to allow videos to be searched based on automatically assigned tags, however, the index is limited to values ​​that match a small number of terms, so that if the user enters a search term that does not match one of the tagged terms, the search will not find any targeted multimedia documents

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 and apparatus for content representation and retrieval in concept model space
  • Method and apparatus for content representation and retrieval in concept model space
  • Method and apparatus for content representation and retrieval in concept model space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Figure 1 depicts an example of a multimedia information retrieval system having features of the present invention. As shown, the user issues a query to the multimedia information retrieval system in step (105) through the user interface (100). Queries are processed by a query processor (101). The query processor searches the stored set of index values ​​(104) in step (106) for a match to the user query. In the case of index values ​​in the form of model vectors, the index values ​​correspond to multidimensional vectors associated with the semantic dimensions of each indexed multimedia document. Matches are passed to the search engine in step (107), and matching multimedia documents are retrieved from the multimedia repository (103) in step (108). Based on the association (110) of the model vector with a particular multimedia document of the repository, a corresponding multimedia document is determined. The multimedia document is then returned to the user in step (109...

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

A method and apparatus for extracting a model vector representation from multimedia documents. A model vector provides a multidimensional representation of the confidence with which multimedia documents belong to a set of categories or with which a set of semantic concepts relate to the documents. A model vector can be associated with multimedia documents to provide an index of its content or categorization and can be used for comparing, searching, classifying, or clustering multimedia documents. A model vector can be used for purposes of information discovery, personalizing multimedia content, and querying a multimedia information repository.

Description

technical field [0001] The present invention relates to indexing multimedia documents using model vectors, and more particularly to methods and apparatus for generating model vector representations, associating model vectors with multimedia documents to provide indexing, and using model vectors to search, classify, and cluster multimedia documents. The invention also relates to the use of model vectors for information discovery, personalization of multimedia content, and querying of multimedia information repositories. Background technique [0002] As the amount of digital information in the form of video, images, text, and other multimedia documents continues to grow, there is an increasing need for more efficient ways of indexing, searching, classifying, and organizing that information. Recent advances in content analysis, feature extraction, and classification are improving the ability to efficiently search and filter multimedia documents. However, there are still signif...

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): G06F17/30G06V20/00
CPCY10S707/99948G06F17/30247G06F17/30265Y10S707/99931G06F17/30858Y10S707/99943G06K9/00624G06F17/3079Y10S707/99945G06F16/7837G06F16/583G06F16/71G06F16/58G06V20/00
Inventor 约翰·史密斯米林德·纳法德阿波斯塔尔·纳特塞夫
Owner INT BUSINESS MASCH CORP