Multiuser Semantic Communication With Concurrent Access for Collaborative Sensing in Internet of Vehicles

While Internet of Vehicles (IoV) networks enhance road safety and driving intelligence through collaborative sensing, reliable data sharing remains a critical challenge due to severe inter-vehicle interference and scarce wireless bandwidth. Conventional orthogonal multiple access often imposes bottlenecks in multiuser semantic communication by failing to accommodate the high heterogeneity of semantic representations among different users. To overcome this, we propose a new context-aware hybrid access framework for Cooperative Semantic Communication (CoSC), which strategically aligns access modes with semantic attributes to maximize fusion efficiency. The fundamental design of CoSC decouples transmission by broadcasting critical semantic information via reliable orthogonal modes to serve as semantic context, while fusion features are aggregated through high-capacity concurrent modes. Within this framework, we first design a context-attentive cooperative channel encoder to align semantic features from different vehicles under the shared context. Next, a semantic fusion-oriented precoding algorithm resolves potential feature conflicts in concurrent channels. Finally, to recover semantic signals from hybrid access modes with a unified receiver, we design a Bayesian-guided score-diffusion algorithm to reconstruct semantic information adaptively from heterogeneous signals. Extensive simulations show that CoSC supports scalable multiuser fusion, yielding a 34.2% improvement in average precision on the OPV2V dataset relative to state-of-the-art methods.