To build the best media library, get the metadata process out of one person’s head and in front of other people and then perform proof-of-concept testing.
Our blog posts came to a pause a couple of weeks ago–right as we started lifting the curtain on Tandem Vault 3 (TV3). Well, that’s no coincidence.
As you think about how to structure your metadata, the method of presentation can be an important consideration as each type of information lends itself to a specific type of interface.
Your use of metadata should be a direct reflection of what’s important to you. The media in your collection, and the subject matter that interests you should drive the tags you make, your workflow, and the software and services with which you manage the collection.
Learn how to try machine learning out for yourself to see if it is going to help you out or waste your time.
Computational tagging can be done by means of linked or linkable data–using a “key” to connect one set of data to another.
Machine Learning and other AI services can add some useful information to a visual library, but they can only tag for things they “understand”.
Computers use two main Machine Learning methods to automatically tag image files, and it is important to know the differences between them.
Computers can be useful in making sense of a media collection, but what’s the difference between Computational Tagging, Artificial Intelligence, Machine Learning and Deep Learning?
Unlike the IPTC location fields, which provide incomplete and sometimes subjective information about a location, GPS data can provide an objectively precise position.