Preprint
Aug 2026
Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing
This work proposes a compositional forensic visual prompt learning framework that operates entirely in the visual feature space and employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units derived from image patches.
Fangling Jiang, Qi Li, Bing Liu et al.
· 0 citations