Personalized Saliency in Task-Oriented Semantic Communications: Image Transmission and Performance Analysis

Semantic communication, as a promising technology, has emerged to break through the Shannon limit, which is envisioned key enabler and fundamental paradigm for future 6G networks applications, e.g., smart healthcare. In this paper, we focus on UAV image-sensing-driven task-oriented semantic communications scenarios. The majority of existing work focused designing advanced algorithms high-performance communication. However, challenges, such energy-hungry efficiency-limited image retrieval manner, encoding without considering user personality, have not been explored yet. These challenges hindered widespread adoption To address above at level, first design an energy-efficient communication framework with triple-based scene graph information. We then new personalized encoder based interests meet requirements saliency. Moreover, study effects dynamic wireless fading channel transmission mathematically thus optimal multi-user resource allocation scheme by using game theory. Numerical results real-world datasets clearly indicate that proposed schemes significantly enhance personalization anti-interference performance are also efficient improve quality services.