SceneSkim - video navigation through multiple metadata streams

[Jonathan Hung]

Hi everyone,

I came across this bit of research from Berkeley VisLab which demonstrates
the potential of using multiple streams of metadata (movie summary,
scripts, and captions) to enhance navigation of a video.

Here's a quote from the abstract:

"We introduce SceneSkim, a tool for searching and browsing movies using
synchronized captions, scripts and plot summaries. Our interface integrates
information from different documents to allow expressive search at several
levels of granularity: Captions provide access to accurate dialogue,
scripts describe shot-by-shot actions and settings, and plot summaries
contain high-level event descriptions. "

I find this work interesting as it cuts across multiple areas of interest:
metadata, content matching and alternatives, and personalized navigation of
visual information.

Relavant links:

   - Project website: http://vis.berkeley.edu/papers/sceneskim/
   - Video demonstrating the research
   <https://www.youtube.com/watch?v=umvD6TGwciE> (contains obligatory Star
   Wars)


Feel free to discuss.

- Jon.
-- 

*JONATHAN HUNG*

INCLUSIVE DESIGNER, IDRC



*T:* 416 977 6000 x3951

*F:* 416 977 9844

*E:* jhung at ocadu.ca



*OCAD UNIVERSITY*

Inclusive Design Research Centre

205 Richmond Street W, Toronto, ON, M5V 1V3



www.ocadu.ca

www.idrc.ocad.ca
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.idrc.ocad.ca/pipermail/fluid-work/attachments/20151110/514168ae/attachment.html>