arXiv 2609.24058 · cs.CV · 2026-09-21
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts
Xingsong Ye, Yongkun Du, Jiaxin Zhang, Zhixian Li, Chong Sun, Chen Li, Jing Lyu, Lianwen Jin 等 9 人
Fudan University
在最新榜 #191 本站收录于 2026-10-21
一句话要点
用按文字体系分路的混合专家，做一个比逐语言模型简单、比大视觉语言模型轻的多语种场景文字识别器。
A script-aware mixture-of-experts gives one multilingual scene-text recogniser that is simpler than per-language models and lighter than VLMs.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：视觉理解与 3D
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲170
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲156
- GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed ▲94
- EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling ▲60
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。