With the introduction of AI scene description to its cloud asset management software, cloud-native asset management company Mimir, part of the Fonn Group, is aiming to improve accuracy and speed up search times with automated, detailed and accurate scene description, natural language search, advanced sharing, and quick cutting capabilities from archive to live.
Mimir uses AI sematic search functionality to detect and describe scenes in a video asset, which according to Fonn Group’s EVP Operations Andre Torsvik, allows users to discover more related content as well as delivering rapid access to assets.
“Semantic searches cover all the associated metadata and everything in the database of assets aswell as the query,” says Torsvik. “It is very different to the traditional way of searching an asset management system; our AI search analyses much more than the tags, meaning search results that contain related content, helping you discover more material.”
Leaning on semantic models to do the heavy lifting enables scene descriptions to be automated, detailed and accurate, with semantic search capabilities allowing users return results based on the meaning of a query and not on its exact wording. It means a query can combine abstract concepts, visual context, and transcript-based content in a regular sentence in the searcher’s language.
Stand Number 7.D05
Company Fonn Group
No comments yet