Metraipolis › archive › dc_ab5fa1a48ff9
From Global Alignment to Local Grounding: Zero-Shot Chinese Character Recognition with Radical Verification — arXiv:2610.09449
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09449
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:47:20.108Z
- SHA-256 of the archived text
717421acd41a38879bff41ad44d8e28298b0646a99a4b1bc5ea6c6f1a6c5e606- Stable URL of this page
https://metraipolis.com/documento/dc_ab5fa1a48ff9
How to cite
From Global Alignment to Local Grounding: Zero-Shot Chinese Character Recognition with Radical Verification — arXiv:2610.09449 — arXiv (en), https://arxiv.org/abs/2610.09449 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab5fa1a48ff9 (Metraipolis archive dc_ab5fa1a48ff9, sha256 717421acd41a38879bff41ad44d8e28298b0646a99a4b1bc5ea6c6f1a6c5e606)
BibTeX
@misc{dcab5fa1a48ff9,
title = {From Global Alignment to Local Grounding: Zero-Shot Chinese Character Recognition with Radical Verification — arXiv:2610.09449},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09449},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab5fa1a48ff9; sha256 717421acd41a38879bff41ad44d8e28298b0646a99a4b1bc5ea6c6f1a6c5e606},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09449. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Zero-shot Chinese character recognition (ZS-CCR) aims to recognize characters whose categories are never observed during training, and typically relies on the compositional structure shared between seen and unseen characters. Recent CLIP-style methods represent this structure with the Ideographic Description Sequence (IDS) and align it with glyph images in a shared embedding space. However, they rely on a single global image--IDS similarity that discards the spatial layout of radicals and, being learned only implicitly from seen classes, generalizes poorly to unseen ones; moreover, global matching often retrieves the correct character within the top candidates yet fails to rank it first when characters differ only in subtle local radicals. To address these issues, we propose a global-to-local two-stage framework. In the first stage, STG-CLIP augments the IDS with explicit tree-position and radical-level geometric priors, yielding a spatial-aware prototype that provides a consistent spatial description across seen and unseen categories for high-recall global retrieval. In the second stage, the Radical Verification Module (RVM) uses the radical instances of each retrieved candidate as queries to verify whether the corresponding radicals can be matched to spatially compatible regions in the input glyph. A margin-based gating rule activates the RVM only when the leading global candidates receive similar similarity scores. Experiments on the ICDAR2013 benchmark demonstrate that our method achieves state-of-the-art performance under the character-level zero-shot setting, obtaining 83.06% top-1 accuracy with 2,755 seen classes. Ablation studies further show that the explicit geometric priors and radical-level verification provide complementary improvements. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.09449 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:18:15.368Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).