Friday, June 12, 2026 | 10:00 a.m. | Room: V1.03 | University of Klagenfurt
Prof. Hui Yong Kim | Dept. of Computer Science and Engineering and Dept. of Artificial Intelligence | Kyung Hee University
Abstract: Up to now, video coding standards have been developed as a combinatory set of a large number of coding tools. Each tool was primarily based on signal-processing algorithms or experimental optimizations. Recently, a new paradigm called Learned Video Coding (LVC), a.k.a. Neural Network-based Video Coding (NNVC), has emerged. By exploiting the end-to-end training with a large number of video datasets, some representative models already outperform the latest video coding standard, VVC (Versatile Video Coding). In this talk, the LVC technology will be briefly outlined and then the opportunities and remaining challenges will be discussed.
Bio: Hui Yong Kim is a Professor in the School of Computing (Dept. of Computer Science and Engineering and Dept. of Artificial Intelligence) in Kyung Hee University, Yongin, Korea since Mar. 2020. He was also an Associate Professor in the Dept. of Electronics Engineering in Sookmyung Women’s University, Seoul, Korea. Prior to joining universities, he served as the Managing Director of Realistic Audio & Video Research Group of Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea from 2005 to 2019. From 2003 to 2005, he worked for AddPac Technology Co. Ltd. as the Multimedia Research Team Leader.
He received his BS, MS, and Ph.D degrees from Korea Advanced Institute of Science and Technology (KAIST) in 1994, 1998, and 2004, respectively. He was also an affiliate professor in University of Science and Technology (UST) and was a visiting scholar in the Media Communications Lab. at University of Southern California (USC), USA. He has published more than 70 papers on international journals and conferences, and holds more than 500 registered patents over the world. He has been an active technology contributor, editor, and ad-hoc group chair in developing several international standards including MPEG Multimedia Application Format (MAF), ITU-T/ISO/IEC JCT-VC High Efficiency Video Coding (HEVC) and JVET Versatile Video Coding (VVC). His current research focus is neural-network based visual data compression, including learned video compression, digital hologram compression and deep feature compression for machine vision.
On 16 April, Dr Felix Schniz (ITEC) organized a guest talk and workshop by Flavia Mazzanti and Manuel Bornell from Immerea (
Flavia Mazzanti and Manuel Bonell are co-founders of Immerea, a Vienna-based indie studio dedicated to VR games and interactive installations. Their interdisciplinary practice explores new modes of perception and interaction in virtual and hybrid spaces, with a strong focus on artistic quality and level of experimentation Their work has been exhibited internationally at institutions and festivals including Ars Electronica (Linz), DIG Shibuya (Tokyo), KunstHaus Wien (Vienna), Kunsthaus Graz, FILE Festival (São Paulo), MESH Festival (Basel), DA Z – Digital Arts Festival Zurich, and ADAF – Athens Digital Arts Festival. Alongside their studio practice, they are both active as university lecturers, speakers, and co-organizers of XR Austria, Austria’s largest community for immersive technologies.
Bio: Als Lead Evangelist bei Celonis inspiriert Rudy Kuhn Kunden, Partner und Analysten dazu, ihre Geschäftsabläufe unter dem Gesichtspunkt von Process Intelligence, Automatisierung und Orchestrierung neu zu gestalten. Mit über 25 Jahren Erfahrung in der Prozessoptimierung und -transformation sowie 16 Jahren tiefgreifender Beschäftigung mit Process Mining hat er seine Karriere darauf ausgerichtet, Unternehmen dabei zu unterstützen, das volle Potenzial ihrer durchgängigen Prozesse auszuschöpfen. Vom Aufbau des ersten E-Business-Beratungsteams von IBM in Deutschland über die Gründung von ProcessGold und die Einführung von Process Mining bei UiPath bis hin zu seiner aktuellen Rolle bei Celonis – Rudy stand und steht weiterhin an der Spitze der digitalen Transformation.
Bio: Hadi Amirpour is working on adaptive video streaming, image/video compression, QoE evaluation, 3D and immersive imaging, and machine-learning-based medical image analysis, with a focus on translating theory into next-generation multimedia systems. He has received multiple distinctions, including Best Paper Awards (PCS 2024, NAB 2025) and Grand Challenge wins at ICIP 2024 and VCIP 2025. He contributes to JPEG Pleno and MPEG standardization on light fields, point clouds, and immersive formats, and has co-chaired Qualinet Task Force 7 since 2021, advancing subjective and objective video quality assessment. He is an Associate Editor for IEEE TCSVT and holds key leadership roles such as TPC Co-Chair of VCIP 2025 and General Co-Chair of QoMEX 2026 and MMSP 2027. He is also active in organizing special sessions, workshops, and tutorials at major venues, including IEEE ICME, IEEE QoMEX, ACM Multimedia, VQEG, EUVIP, and ACM MobiSys.
Short CV: I’m a Professor at the University of Kassel, where I head the Distributed Systems group. Before, I was a professor at Brandenburg University of Technology and headed the Computer Networks group. Prior to that, I was at RWTH Aachen University, and before that, I was with Anja Feldmann at TU Berlin / Deutsche Telekom Innovation Laboratories. I was a visiting scholar at the group of Paul Barford at the University of Wisconsin–Madison, USA.
