Prof. Mohamed Deriche

Prof. of AI/ML
College of Engineering and Information Technology
Ajman University, Ajman, United Arab Emirates

Education

  • Ph.D., Signal Processing from the University of Minnesota in 1994,
  • B.Sc. degree in Electrical Engineering from the National Polytechnic School, Algeria,

Biography

Mohamed Deriche received his B.Sc. degree in electrical engineering from the National Polytechnic School, Algeria, and his Ph.D. degree in signal processing from the University of Minnesota in 1994. He worked at Queensland University of Technology, Australia, before joining King Fahd University of Petroleum and Minerals (KFUPM) in Dhahran, Saudi Arabia, where he led the signal processing group. He has published more than 300 papers in multimedia signal and image processing. In 2021, he joined Ajman University to promote  the AIRC centre and the new Masters in AI within the College of Eng and IT. He delivered numerous invited talks and chaired several conferences including GlobalSIP-MPSP, IEEE Gulf (GCC), Image Processing Tools and Applications, and TENCON (a Region 10 conference). He has supervised more than 50 M.Sc. and Ph.D. students and is the recipient of the IEEE Third Millennium Medal. He also received the Shauman Best Researcher Award, and both the Excellence in Research and Excellence in Teaching Awards while at KFUPM and at Ajman University. He is ranked in the top 0.5% scientists according the GPS Scholar ranking and in the top 80 achieved scientists in UAE. His research interests cover signal and image processing spanning from theory to models to diverse applications in multimedia, biomedical, seismics, to language processing.

Title :

When Multimedia Quality of Experience meets Artificial Intelligence

With the advancement of technology. the need to automatically evaluate the quality of multimedia content whether audio, images, or videos, has become an important part of most multimedia systems based on machine learning and computer vision principles. While current objective multimedia quality metrics have shown high correlation with subjective scores, nevertheless, we still face many challenges. This includes but is not limited to difference in the performance of metrics across various datasets and distortions, dealing with multiple distortions, run-time performance, memory requirements, application-specific metrics, etc. Ensuring and enhancing quality has become a paramount concern. In this talk, we explore the intersection of multimedia content evaluation, advances made in AI/ML, and the transformative capabilities of Generative Artificial Intelligence (AI). The presentation will identify the approaches and tools that are used to gauge the excellence of multimedia content in various media and their forms.

We will start by enumerating the challenges, risks and difficulties of standard multimedia ratings in present-day society due to the fact that in the evaluation, each multimedia representation almost touches on elements of visual aesthetic perception of the images, the sound, animations, difficultly/ ease in comprehension and user interactivity. We underline that this more contextual understanding of multimedia is unrevealed in traditional evaluation procedures.

The talk then shifts focus to the promising role of Generative AI tools in overcoming these challenges. We provide an overview of the latest advancements in models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). Lastly, the presentation concludes with a forward-looking perspective, addressing ethical considerations, and future directions in the relationship between multimedia content evaluation and AI and generative AI. The goal is to present  a roadmap for unlocking the potential of AI and generative AI in enhancing QoE evaluation tools and in  offering valuable insights for industry professionals, researchers, and enthusiasts.