Vortrag | Judith Redi, Delft University of Technology

Titel

Modern multimedia technologies are challenged to handle every day bigger quantities of visual information with a limited set of resources (e.g. bandwidth, storage space). As the multimedia consumption grows, so do user expectations in terms of Quality of the delivered Experience. Multimedia systems can be optimized (from intelligent adaptive streaming to perceptual coding), but in order to steer such optimization, mechanisms are needed that allow assessing the quality of the delivered multimedia experience at any stage of the delivery chain.

In this talk, I will review the current challenges in assessing the quality of multimedia experiences, both from a computational and a human point of view. On the computational side, I will poke into how and why Machine Learning can be used to successfully predict Quality of Experience (QoE), and more specifically the annoyance of visual distortions. On the human side, I will review a set of methodological challenges (and a few solutions) related to subjective QoE measurement. Finally, I will look at the future, giving some insight on how user factors other than physiology and perception can influence Quality of experience and can be factored into automatic image and video quality assessment methods.

Speaker’s Bio

Judith Redi is Assistant Professor at the Faculty of Electrical Engineering, Mathematics and Computer Science (EECMS) of Delft University of Technology. Her work involves the understanding and modelling of user appreciation for multimedia experiences. This connects visual perception, cognitive science and engineering, machine learning and computer vision. She obtained her PhD from the University of Genoa in 2010, and thesis received the best thesis award from the same university. After a post-doc period at Eurecom, France, working on digital image forensics and computer vision, she moved to the Intelligent Systems department of TU Delft, and recently she was awarded a NWO-VENI-grant for her research proposal on “Semantic Aware Quality Assessment”. She is currently member of a number of technical program committees of top conference, and recently she has been Technical Program Committee Chair of QoMEX 2015 and Area Chair for multimedia HCI and QoE at ACMMM 2016. She is also associate editor for the IEEE transactions on Multimedia, and will be General Chair for ACM TVX in 2017.