Metadata and media: Shared AI project approved!14 Mar 2023
The digital meemoo archive contains a huge amount of audiovisual content. Now, as part of the Gecoördineerd Initiatief voor Erfgoeddigitalisering (GIVE - ‘Coordinated Initiative for Heritage digitisation), we’re addressing the fact that this content is not easily searchable, due to a lack of descriptive metadata, for the government and cultural sector. And now we have some good news for the media sector as well, because the Shared AI project has been approved to launch at the end of the year.
In order to stimulate technological innovation in the media sector, Flemish Minister Benjamin Dalle last year announced a call for tenders for this digital transformation project. Together with VRT (Flemish public broadcaster) and regional broadcasters, we submitted a project for media content metadata enrichment in a regional context. And it was approved at the end of last year! So, from the end of this year, we will be focusing on speech, entity and facial recognition, just like in the GIVE project. Together, we’re building a solid foundation for more uniform metadata across different media.
Using metadata to describe content from different partners together at the same time is a unique and extremely valuable process. This approach makes it possible, for example, to identify individuals across different content and even from different partners. Combining metadata and linking it to an external source such as Wikidata also makes the content easy to search.
This project is part of the Flemish Government’s Resilience Recovery Plan.