EUVIMEDEUVIMED entdecken
Crossref

Edge Intelligence-Empowered Immersive Media

Zhi Wang, Jiangchuan Liu, Wenwu Zhu

IEEE MultiMedia · 2023-04 · 30 (2) · 8-17

DOI: 10.1109/mmul.2023.3247574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE MultiMedia, 2023-04. Verfasst von Zhi Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 17 Literaturangaben. Gefördert von: Shenzhen Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent years have witnessed many immersive media services and applications, ranging from 360° video streaming to augmented and virtual reality (VR) and the recent metaverse experiences. These new applications usually have common features, including high fidelity, immersive interaction, and open data exchange between people and the environment. As an emerging paradigm, edge computing has become increasingly ready to support these features. We first show that a key to unleashing the power of edge computing for immersive multimedia is handling artificial intelligence models and data. Then, we present a framework that enables joint accuracy- and latency-aware edge intelligence, with adaptive deep learning model deployment and data streaming. We show that not only conventional mechanisms such as content placement and rate adaptation but also the emerging 360° and VR streaming can benefit from such edge intelligence.

Förderung

  • Shenzhen Science and Technology Program

Zitieren

APA

Wang, Z., Liu, J., & Zhu, W. (2023). Edge Intelligence-Empowered Immersive Media. IEEE MultiMedia, 30(2), 8-17. https://doi.org/10.1109/mmul.2023.3247574

Vancouver

Wang Z, Liu J, Zhu W. Edge Intelligence-Empowered Immersive Media. IEEE MultiMedia. 2023;30(2):8-17. doi:10.1109/mmul.2023.3247574

BibTeX
@article{Wang2023,
  author = {Wang, Zhi and Liu, Jiangchuan and Zhu, Wenwu},
  title = {Edge Intelligence-Empowered Immersive Media},
  journal = {IEEE MultiMedia},
  year = {2023},
  volume = {30},
  number = {2},
  pages = {8--17},
  doi = {10.1109/mmul.2023.3247574}
}
Kostenlos starten →