The present invention relates to a system for generating a description
record from multimedia information including, e.g., video data. A
multimedia information input interface is used to receive multimedia
information. A computer processor receives the multimedia information,
processes the video information by performing video object extraction
processing to generate video object descriptions from the video
information, processes the generated video object descriptions by object
hierarchy construction and extraction processing to generate video object
hierarchy descriptions, and processes the generated video object
descriptions by entity relation graph descriptions.