Multiple Image Distortion DNN Modeling Individual Subject Quality Assessment

• Published in: ACM transactions on multimedia computing communications and applications Vol. 20; no. 8; pp. 1 - 27
• Main Authors: Fotio Tiotsop, Lohic, Servetti, Antonio, Pocta, Peter, Van Wallendael, Glenn, Barkowsky, Marcus, Masala, Enrico
• Format: Journal Article
• Language: English
• Published: New York, NY ACM 29.06.2024
• Subjects: Computing methodologies; Information systems; Machine learning; Multimedia information systems; synthetic labels; individual quality perception; transfer learning; artificial intelligence-based observers; Individual image quality assessment

A recent research direction is focused on training Deep Neural Networks (DNNs) to replicate individual subject assessments of media quality. These DNNs are referred to as Artificial Intelligence-based Observers (AIOs). An AIO is designed to simulate, in real-time, the quality ratings of a specific i...