A Prime Video paper discusses one of the fundamental clustering techniques in machine learning, examining its key performance factors, and revealing the underlying mechanism used to find the clusters.
Prime Video uses computer vision and video understanding techniques to detect different video content segments, such as introductions, recaps, and opening or ending credits.
BA Winston, VP of Technology at Prime Video, highlights five research areas during official launch of UT Austin-Amazon Science Hub.
A week in the life of Franco Raimondi, an Amazon Scholar at Prime Video and Professor at Middlesex University.
Prime Video announces ARA awards in the fields of anomaly detection and insights, automated reasoning, personalization and discovery, and video quality analysis.
As head of Design Ops, UX Research, and Global Commerce Design at Prime Video, Amélie helped oversee the redesign of the user experience – a journey that’s allowed her to embrace Amazon’s Leadership Principles while empowering her colleagues.
Research by Prime Video demonstrates that it’s vital to consider both spatial and temporal features when developing a model to estimate the visual quality of production-related content.
Prime Video achieves a 99.4% F1 score in synchronizing dubbed audio to non-dubbed audio using an innovative, fast, and memory-efficient approach.
In this work, we develop a multiscale audio spectrogram Transformer (MAST) that employs hierarchical representation learning for efficient audio classification.