Title: Machine learning for multimedia communications
Authors: Nikolaos Thomos, Thomas Maugey, Laura Toni
Abstract: Machine learning is revolutionizing the way multimedia information is processed and transmitted to users. After intensive and powerful training, some impressive efficiency/accuracy improvements have been reached all over the transmission pipeline. For example, the high model capacity of the learning-based architectures enables to accurately model the image and video behavior such that tremendous compression gains can be achieved. Similarly, error concealment, streaming strategy or even user’s perception modeling have widely benefited from the recent
learning-oriented developments. However, learning-based algorithms often imply drastic changes on the way data is represented or consumed, meaning that the overall pipeline can be affected even though a subpart of it is optimized. In this paper, we review the recent major advances that have been proposed all over the transmission chain, and we discuss their potential impact and the research challenges that they raise.