AI in Production – training and targeting

Loading

AI in Production – training and targeting

13 Sep 2024
Conference Room 2
Conference (Technical Papers)

In this session, three authors present their work on the application of AI to media production. Our first paper from the EBU describes a facial recognition machine learning system that has been tailored to the specific needs of media documentalists. It seeks to only identify “active” and not incidental characters, assisting in compliance with privacy regulations. Our second paper, from NHK, presents a solution to the over-training problem when applying machine learning to multi-label indexing of news items, this is especially important for infrequently classified events. It provides good performance and has been trialled, with the authors also acknowledging its limitations. Our final paper, from Viaccess-Orca, looks to a future where Generative AI is used to adapt advertising based on characteristics / beliefs that have been gleaned of the target. Used in a closed loop, the Generative AI can test, score and adapt the media to maximise its impact!

Speakers
Alain Nochimowski, CTO - Viaccess-Orca
Yuki Yasuda, Researcher - NHK (Japan Broadcasting Corporation)