METHOD FOR REPRESENTING AND COMPARING MULTIMEDIA CONTENT

Patent №

US 6,546,135

Granted

2003-04-08

Filed 1999

Owner

MITSUBISHI ELECTRIC INFORMATION TECHNOLOGY CENTER AMERICA, INC.

Lab

AI components

6

ml · nlp · vision · speech · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

09385169

A method for generating a representation of multimedia content by first segmenting the multimedia content spatially and temporally to extract objects. Feature extraction is applied to the objects to produce semantic and syntactic attributes, relations, and a containment set of content entities. The content entities are coded to produce directed acyclic graphs of the content entities, where each directed acyclic graph represents a particular interpretation of the multimedia content.

AI classification

Natural language1.00
Machine learning1.00
Speech1.00
AI hardware1.00
Knowledge representation0.99
Vision0.97
Planning0.01
Evolutionary computation0.00

Ownership

MITSUBISHI ELECTRIC INFORMATION TECHNOLOGY CENTER AMERICA, INC.

assignment · 102150503

Assignors

LIN, I-JONG, VETRO, ANTHONY, DIVAKARAN, AJAY, KUNG, SUN-YUAN

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC