Machine Learning for Multimedia Communications

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 made all over the transmission pipeline. For example, the high model capacity of the learning-based architectures enables us to accurately model the image and video behavior such that tremendous compression gains can be achieved. Similarly, error concealment, streaming strategy or even user perception modeling have widely benefited from the recent learning-oriented developments. However, learning-based algorithms often imply drastic changes to the way data are 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 across the transmission chain, and we discuss their potential impact and the research challenges that they raise.

Exploring Computing Paradigms for Electric Vehicles: From Cloud to Edge Intelligence, Challenges and Future Directions

“…[39][40][41]. Real-time video analytics, built on computer vision, emerges as a killer application for Edge intelligence due to its high computational demands, bandwidth requirements, privacy concerns, and low-latency needs [42]. Multiple benefits of Edge intelligence have created a path for expanded progression in the near future [43].…”

Taking a “Deep” Look at Multimedia Streaming

“…This multimedia streaming process goes through several steps during transmission. 1 1) Source coding: This step compresses the data by removing temporal and spatial redundancies. 2) Channel coding: This step is for (wired/wireless) network transmission to handle communication errors (including packet losses) as well as to address security.…”