The overarching goal of the Informedia
initiatives is to achieve machine
understanding of video and film media,
including all aspects of search,
retrieval, visualization and
summarization in both
contemporaneous and archival content
collections.
The base technology developed under
Informedia-I combines speech, image
and natural language understanding to
automatically transcribe, segment and
index linear video for intelligent search
and image retrieval. Informedia-II seeks
to improve the dynamic extraction,
summarization, visualization, and
presentation of distributed video,
automatically producing "collages" and
"auto-documentaries" that summarize
documents from text, images, audio
and video into one single abstraction.
on the web
Informedia Home Page
http://www.informedia.cs.cmu.edu/