The review of the TEWI colloquium of Dr.-Ing. Christian Keimel from May 9, 2019 comprises the video and slides (below):
Abstract: Artificial Intelligence (AI) is nowadays used frequently in many application domains. Although sometimes considered only as an afterthought in the public discussion compared to other domains such as health, transportation, and manufacturing, the media domain is also transformed by AI enabling new opportunities, from content creation e.g. “robojournalism” and individualised content to optimisation of the content production and distribution. Underlaying many of these new opportunities is the use of AI in its current reincarnation as deep learning for understanding the audio-visual content by extracting structured information from the unstructured data, the audio-visual content.
In this talk the current understanding and trends of AI will therefore be discussed, what can be done, what is done, and what challenges remain in the use of AI especially in the context of media applications and services. The talk is not so much focused on the details and fundamentals of deep learning, but rather on a practical perspective on how recent advances in this field can be utilised in use-cases in the media domain, especially with respect to audio-visual content and in the broadcasting domain.
Bio: Christian Keimel received his B.Sc and Dipl.-Ing.(Univ.) in information technology from the Technical University of Munich (TUM) in 2005 and 2007, respectively. In 2014 he received a Dr.-Ing. degree from TUM for his dissertation on the “Design of video quality metrics with multi-way data analysis.” Since 2013 he is with the Institut for Rundfunktechnik (IRT), the research and competence centre of the public service broadcasters of Austria, Germany, and Switzerland, where he leads the machine learning team, working on the applications of machine learning and AI in the broadcasting context. In addition, he is a lecturer at TUM for “Deep Learning for Multimedia”. His current research interests include applications of data-driven models using machine learning particularly deep learning for audio-visual content understanding and distribution optimisation.