Preprint
Aug 2026
Grounding and Explaining Visual Evidence for AI-Generated Image Detection in Human-Centric Scenes
This work presents HAVE (Human-centric AI-generated Visual Evidence), a diverse human-centric dataset, and proposes PAVE, a Perception-Aware Visual Evidence framework that jointly performs authenticity prediction, visual evidence grounding, and region-aligned explanation generation.
Kun Guo, Yu-Zhou Yang, Haoyue Wang et al.
· 0 citations