Efficient Caption-Based Retrieval of Multimedia Information

Abstract

We describe MARIE-1 and MARIE-2, information retrieval systems for multimedia data. They exploit captions on the data and perform natural-language processing of them and English retrieval requests. Some content analysis of the data is also Performed to obtain additional descriptive information. The key to getting this approach to work is sufficient fast processing. We achieve this by decomposing the problem into information filters and applying a new theory of optimal information filtering which we have developed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 09, 1993
Accession Number
ADA279604

Entities

People

  • Neil C. Rowe

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Air Platforms
  • Human Systems
  • Weapons Technologies

DTIC Thesaurus Topics

  • Aircrafts
  • Artificial Intelligence
  • Classification
  • Computer Languages
  • Computer Science
  • Computers
  • Databases
  • Filters
  • Information Processing
  • Information Retrieval
  • Information Science
  • Information Systems
  • Language
  • Media
  • Multimedia
  • Natural Language Processing
  • Natural Languages

Fields of Study

  • Computer science

Readers

  • Business Analytics
  • Database Systems and Applications
  • Operations Research

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Learning Algorithms