Join the seminar online

Abstract

Delivering high quality streaming video requires effective detection of audio-visual defects at massive scale. In this talk, I will present how my team Video Quality Analysis tackles this critical challenge in Amazon Prime Video. I will introduce common AV defects, discuss the technical hurdles in building scalable media defect detectors, and dive into challenges around handling creative intent and defining appropriate performance metrics. Finally, I will share perspectives on ongoing research to advance audio-visual defect detection and enhance streaming quality across evolving content formats.

Biography

Alex Mackin is a senior applied scientist at Amazon Prime Video, where he leads the research, development and implementation of high-performing and scalable algorithms for media defect detection. Prior positions include image processing sector head in AI research and computer vision at MBDA and chief technology officer of RIDLE, a startup specializing in resilient video compression. Alex completed his PhD in Electrical and Electronic Engineering at the University of Bristol in 2017 supervised by Professor Dave Bull. His thesis focused on the human impact of new immersive video formats such as high frame rate (HFR) and ultra-high definition (UHD). Additionally, Alex leads Amazon's external collaboration with universities and is a co-chair of the BMVA Sullivan Thesis prize.