In many types of content, lower-third graphics contain valuable information. Up until 2022, archivists at VRT used lower thirds character graphics as a visual source of data for manual annotation. This meant scrubbing through footage, looking for occurrences of lower-third graphics, and entering the metadata manually into the system. In this presentation, Marijn Daniels will explain how VRT used A.I. to automate the process of speaker labelling, using lower-third character recognition.

Marijn Daniels holds a Masters degree in computer science. At VRT, Marijn works as a Technology project manager and product owner. In his 23-year-long career at VRT, he had the opportunity to work on the transformation of VRT from a tape-based workflow to file-based production, first in SD and later upgrading VRT production to HD. Since 2019, Marijn has been responsible for all Technology projects regarding the VRT Archive.

For the last decade INA has engaged in a wide digital transformation. The fresh redesign of our data model quickly allowed to experiments with AI based tools such as machine learning. This speech aim to present the solution we built to assist the documentary processing of TV news channel and will focus on the business aspects. What changes do recent technical progresses bring for the librarians and heritage community?

Anne Couteux is a project manager in the unit Management of Data and Media. She is in charge of the standards of the description of the audiovisual archive content of the controlled vocabularies, among which the thesaurus is used to describe, index and retrieve the Ina multimedia archives. She is currently involved in the refoundation of the collections management IT system, including a new data model and artificial intelligence technologies.

—

Olivio graduated in audiovisual & heritage management after studying movies and visual arts. He joined Ina as an intern in 2019, assigned to an experimental and cross-departmental mission focused on experimenting with AI-based solutions. Working alongside data scientists and media librarians, trained in machine learning models management, he contributed to developing automatic segmentation and indexing processes for TV content as a go-between and participated in changing management. Since 2020, Olivio joined the Data Department and serves as a project manager and product owner to pursue the coordination of various AI projects.