Preprint
Oct 2026
From Global Alignment to Local Grounding: Zero-Shot Chinese Character Recognition with Radical Verification
This work proposes a global-to-local two-stage framework for zero-shot Chinese character recognition that achieves state-of-the-art performance under the character-level zero-shot setting, and shows that the explicit geometric priors and radical-level verification provide complementary improvements.
Yu-Heng Shih, Bing-Chen Wu, Tsz-To Wong et al.
· 0 citations