SST-V: A Scalable Semantic Transmission Framework for Video

Abstract: The emerging new services in the sixth generation (6G) communication system impose increasingly stringent requirements and challenges on video transmission. Semantic communications are envisioned as a promising solution to these challenges. This paper provides a highly-efficient solution to video transmission by proposing a scalable semantic transmission algorithm, named scalable semantic transmission framework for video (SST-V), which jointly considers the semantic importance and channel conditions. Specifically, a semantic importance evaluation module is designed to extract more informative semantic features according to the estimated importance level, facilitating high-efficiency semantic coding. By further considering the channel condition, a cascaded learning based scalable joint semantic-channel coding algorithm is proposed, which autonomously adapts the semantic coding and channel coding strategies to the specific signal-to-noise ratio (SNR). Simulation results show that SST-V achieves better video reconstruction performance, while significantly reducing the transmission overhead.

Keywords: scalable coding; semantic communication; video transmission