2. Semantic Media – Problem Area
TV Productions Music / Radio Productions
Consumer: How to find relevant content in large media collections?
Producer: How to monetize, how to subvert piracy?
Film Productions Photo Productions
Source of images: Google
3. Navigation in Content Collections:
Previous Approaches
Automatic annotations often not as detailed and robust as needed
Reason: Automatic methods have no access to knowledge only
available during production
User interfaces are not as rich as needed
Reason: Metadata does not incorporate relevant external
information
4. Semantic Media - Concept 1:
Annotation As Part of Production Workflow
Employing knowledge of the production process leads to simplified
and hence more robust (automatic) metadata generation
procedures
Integrating additional information usually discarded after production
allows for richer annotations
Resulting novel workflow systems facilitate automation and
assist content producers as well consumers throughout the
content life-cycle
5. Semantic Media - Concept 1: Example
Metadata: Where was this picture taken?
What is in it? What’s the weather like?
Source of image: Wikipedia
6. Semantic Media - Concept 1: Example
Metadata: Who are the actors (in this episode)?
What are the story lines?
7. Semantic Media - Concept 2: Incorporating Global
Knowledge Using Linked Data Technology
Managing and exposing enhanced metadata using
semantic web and linked data technology allows for uniting
various sources of information and thus improving the user
experience with richer interfaces
8. Semantic Media - Concept 2: Example
BBC Music website
+
Structured Wikipedia Data
=
Improved User Experience
More about this later…
9. Goals of the Semantic Media Project
Creating a forum for researchers / developers
Encouraging interdisciplinary research bringing together
specialists across the entire ICT sector
Sparking new collaborations between researchers
(including industry partners) by funding mini-projects,
student exchanges and internships
Encourage leading researchers to develop roadmaps
guiding the direction of future research efforts and grant
applications
Encourage substantial grant applications: UK & EU
10. Semantic Media – The Network
Future challenges and opportunities require researchers from
across the ICT landscape to contribute and collaborate
EPSRC priority “Working Together”
Semantic Media Network as a hub for future collaborative
grant applications
11. Funding - Opportunities and Examples
Exchange of students across working groups and internships / placements
Construction of ontologies appropriate for 3D+t content description (sound, video,
objects)
Capturing of motion information in a film/tv set to capture scene-descriptive
metadata to associate with the primary media stream (i.e. video)
Fusion of metadata from disparate sources to build a composite metadata
stream associated with a single media stream, propagating through the value chain
from producer to consumer, e.g:
Metadata from several musical instruments to create a composite harmony
stream
Motion metadata streams from several actors in a scene to create a composite
action stream
Combining rights-related metadata (e.g. using MPEG Value Chain Ontology [9]),
user generated and other tags downstream from creation
Application of temporal logic on (time-structured) media metadata streams [8]
Use of capture-at-source metadata to enhance the production workflow
Ethnographic studies of metadata-enhanced production tools to assess their
fitness for purpose
12. Funding - Application
1.) Short semi-formal application
2.) Steering committee selects best ideas
3.) Start working
Funding available for 10-20 projects £10k-£50k each
More details on the website soon…
13. Getting involved
Just the beginning forming a network. Participate by:
Join our mailing list for announcements and discussions (soon to come
and you will be informed about it)
Have an idea for a feasibility study and put it on our idea-wiki
Become an active member of the steering committee
Help organizing meetings (maybe focused on a specific subfield)
Help documenting the research landscape by participating in the
landscape-wiki
Participate in future meetings, sandpits, tutorials, as well as
collaborative grants and paper submissions
Help identifying people who might be interested in this network and
invite them (or tell us)
Check our website: semanticmedia.org.uk
14. Programme For Today
09:00 Registration and Welcome Coffee
09:30 Project Introduction: Mark Sandler (Queen Mary, University of London)
Invited talk: Karlheinz Brandenburg (Director of the Fraunhofer Institute
for Digital Media Technology, Illmenau, Germany): Extraction of
09:45
metadata from media data: From music recommendation to recognition
of big apes
Networking Event: 60 second quick-fire summaries of the participants'
10:45
background and interests.
12:00 Fingerfood Buffet with Poster Presentations and Demos
Invited Talk: David De Roure (Director of the Oxford e-Research
13:30
Centre, University of Oxford)
14:30 Coffee Break
15:00 Invited Talk: Yves Raimond and David Rogers (BBC)
16:00 Networking Event: "Speeddating"
17:00 End
Notas do Editor
The profusion of digital content now available to an individual, average consumer/viewer/listener is over-whelming, potentially forcing consumers into increasingly narrow bands of media experience as they retreat to limiting choices as a coping strategy. Professional recommenders, such as newspaper film and TV reviewers, are similarly overwhelmed, and paradoxically, more relied upon by consumers whilst considered less relevant as alternative automated and semi-automated recommendation systems emerge: for movies (e.g. The Netflix competitions), music (e.g. last.fm), or books (e.g. Amazon).
Examples:1.) Taking a photoAfter taking the photo one could have the idea that it makes sense to annotate the picture with the place it was taken at.One way could be to first take the picture and then employ a massive database consisting of millions of pictures of places to estimate where the picture was taken.Another way could be to put a little inexpensive GPS sensor into the camera and slightly extend the production workflow by storing the current GPS location along the image data.Which approach do you think would be more successful?=> Such cases is what we are interested in. How can the workflow be extended do make things much easier?2.) Annotating music recordingsLyrics extraction very hard from final recording but in the studio with multitrack much easier and automatic.