DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning

ArXi:2603.28251v1 Announce Type: cross Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception patterns and advance visual attention prediction for intelligent vehicles, we propose DiffAttn, a diffusion-based framework that formulates this task as a conditional diffusion-denoising process, enabling accurate modeling of drivers' attention.