Contextual Wireless Video Semantic Communication in MIMO-OFDM Systems

2026-05-03

AI Summary

This work addresses the inefficiency and semantic fragility of conventional separated video transmission over multipath MIMO channels by proposing a MIMO-OFDM-based contextual video semantic transmission framework, termed M-CVST. The framework introduces an innovative context–subcarrier correlation mapping mechanism that dynamically aligns video semantic features with MIMO subcarrier groups. It further integrates recursive subcarrier sampling and temporal channel state information (CSI) embedding to enhance the channel awareness of the entropy coding model. Experimental results demonstrate that M-CVST significantly outperforms existing semantic communication and traditional schemes in multipath environments, achieving notable improvements in both video reconstruction quality and semantic fidelity.

Abstract

This paper proposes a MIMO-OFDM-based context video semantic transmission framework, namely M-CVST, for robust video communication over multi-path multiple-input multiple-output (MIMO) channels. It introduces a context-subcarrier correlation map that aligns video feature context with groups of MIMO subcarriers. To leverage the time-correlated nature of multi-path channels, a recursive subcarrier sampling method paired with time-correlated reference embedding is designed, enabling the use of previously sampled MIMO subcarrier CSI to enhance channel state awareness in the entropy coding model. Numerical results verify the superiority of proposed M-CVST over MIMO multi-path channels compared to other semantic schemes and traditional separated schemes.

Problem

• semantic communication
• MIMO-OFDM
• video transmission
• multi-path channels
• context awareness

Innovation

• MIMO-OFDM
• semantic communication
• context-subcarrier correlation
• recursive subcarrier sampling
• time-correlated embedding