Kick-off meeting on February 24th 2017 for the Linkflows project, a collaboration between the Web & Media Sciences Group, Computer Science Department, Vrije Universiteit Amsterdam, IOS Press and Netherlands Institute for Sound and Vision.
5. Relevant background
Research and academic projects
INVENiT: semantic web, Linked Data, crowdsourcing
Accurator: working with the Rijksmuseum collection
DigiBird: integrate online collections, different media
Practical experience: IT company
Education: Computer Science, Bioinformatics
7. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews
8. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts
9. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects
10. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries
11. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations
Note
12. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations, discussions, etc.
Note
13. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations, discussions, etc., better valorized and efficiently assessed
14. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations, discussions, etc., better valorized and efficiently assessed in
a way that allows for their automated interlinking
Note
15. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations, discussions, etc., better valorized and efficiently assessed in
a way that allows for their automated interlinking
Dataset
16. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations, discussions, etc., better valorized and efficiently assessed in
a way that allows for their automated interlinking, quality evaluation
TheGradStudentWay.com
YESSS!
I finished it!
17. Linkflows in a nutshell
Can we make scientific contributions on the Web, e.g. articles, reviews,
blog posts, multimedia objects, datasets, individual data entries,
annotations, discussions, etc., better valorized and efficiently assessed in
a way that allows for their automated interlinking, quality evaluation
and inclusion in scientific workflows?
Note
18. Approaches
1. Automated interlinking - Publishing Infrastructure
Provenance-aware semantic modeling
2. Quality evaluation - Assessment framework
Crowdsourcing, expert nichesourcing
Information extraction and machine learning
3. Inclusion in scientific workflows - Data Science Journal
20. We`re just getting started!
Follow us:
http://vu-amsterdam-web-media-group.github.io/linkflows/
21. Discussion
Data sources
Use Cases: semantic publishing + multimedia objects
Logistics and supervision
Schedule follow-up meetings
Workshops or specific activities and venues
22. Web & Media group
Lora Aroyo, Davide Ceolin, Tobias Kuhn
31. 2
• STM Publisher since 1987, 30 years in 2017
• Based in Amsterdam, the Netherlands
• 25 people working in the Amsterdam office
• Publishing ~85 journals, >80.000 journal articles
online
• >1000 Books (online)
32. 3
• Medicine and Health
• Chemistry
• Computer and Communication
Sciences
• Engineering and Technology
• Environmental and Energy Sciences
• Life Sciences
• Materials Science
• Mathematics
• Social and Information Sciences
36. Johan Oomen
Head of Research
Netherlands Institute for Sound and Vision
Innovation at Sound and Vision
Linkflows
@johanoomen
37. “We enable everyone to utilize the
collections to learn, experience and create.”
38. Film from 1898 onwards
Television from 1951
Advertising 1920
Cinema journals ‘22–’80
Radio from 1934
Dutch royal family collection
Dutch football league archive
National Music Archive
Objects related to media
Web video
Amateur film
Documentary film
Photographs
Websites
Visual art collections
…and much more.
a million hours
39.
40. “Images for the Future” digitisation programme (2007-2014)
137.200 hours video MXF SD (HD for Film)
17.510 hours film (DPX and MXF)
123.900 hours audio WAF
1.200.000 photo’s TIFF
http://beeldenvoordetoekomst.nl/publicatie/
42. A
annual ingest:
8.000 hrs video
54.000 hrs radio
=
~1,5 petabyte
Visuals https://vimeo.com/51425368 - Sebastiaan ter Burg CC-BY
43. Sound and Vision - Channels
general public
media studies scholars
44. Sound and Vision - Channels
general public through 3rd party platforms
open collections: access through syndication
www.openimages.eu
45. Research and Innovation agenda: 5 topics
…in collaboration with universities and other research partners
Access, use
and context
Digitisation
&
Digital
Durability
Metadata UsersHumanities
56. Low-level features
Multimedia
content analysis
today sniper fire disrupted the funeral of an
eleven year old ethnic albanian boy he was
killed yesterday while while chopping wood
his family blames serb police before his death
louisiana state police now say six workers
were killed after a natural gas well exploded
and caught fire about forty five miles east of
shreveport four others were injured in
yesterday's blast a police spokesman says the
derek started to melt in the intense heat the
Audio transcripts Concept detectors
Speaker identification Face recognition
Machine analysis
59. Two-speed IT
1. Solid foundation (MAM system)
2. Open source software from R&D
3. Agile in-house software development
4. Collaboration with spin-offs (customization,
processing, support)
61. Technology transfer - the Accelerator Team
R&D Development ICT
Daily&produc-on&Demonstrators&
62. Technology transfer - the Accelerator Team
R&D Development
Production &
Maintenance
Products, not
projects
Incremental
development
Demo every two
weeks
Daily&produc-on&Demonstrators&
Multi-annual
research agenda
Collaborative
projects
Day-to-day
maintenance
Contact with 3rd
parties
63. Technology transfer - the Accelerator Team
R&D Development ICT
Daily&produc-on&Demonstrators&
spin-off SME’s
64. Entity extraction
Extracting keywords from the thesaurus from
subtitles
=> import in MAM system
Currently working with two services
x-TAS (University of Amsterdam)
Textrazor
Reseach partners Spin-off SME
65. Entity extraction
Victor de Boer, oeland J.F. Ordelman and Josefien Schuurman: ‘Practice-oriented
Evaluation of Unsupervised Labeling of Audiovisual Content in an Archive Production
Environment.’ (to appear)