[
Lists Home |
Date Index |
Thread Index
]
Yes. Human annotation is always possible for adding
the metadata but the other systems that use feature
extraction are highly context or event type dependent
as to the semantic of the features that can be
extracted based on the physical characteristics that
can be measured. Generalization is possible but at
the cost of precision of search. Again, it
comes down to tradeoffs of certainty and uncertainty.
We can't get beyond Heisenberg.
I suspect that having automatic analysis systems isn't
far off though. AFAICS, the technical barriers aren't
significant and it comes down to usable reach for not
very rich searching.
len
From: Ken North [mailto:kennorth@sbcglobal.net]
> >2. Yahoo has recently taken the RSS approach. Video RSS provides a text
> >description such as height, width, bitrate and running time:
> >http://www.webservicessummit.com/Channels/WebServicesSummitAudioVideo.rss
>
> Which is ok for knowing something about the coffee cup but not the coffee.
This is an example that goes to the heart of this thread.
There is an element for describing the video / audio program when you create
the
RSS feed. It's low tech and depends on human interpretation, but it's the
only
game in town until search engines offer automatic content analysis for video
and
audio.
|
