当前位置:
X-MOL 学术
›
Sci. China Inf. Sci.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Scene text recognition via dual character counting-aware visual and semantic modeling network
Science China Information Sciences ( IF 8.8 ) Pub Date : 2024-02-05 , DOI: 10.1007/s11432-023-3935-8 Ke Xiao , Anna Zhu , Brian Kenji Iwana , Cheng-Lin Liu
更新日期:2024-02-09
Science China Information Sciences ( IF 8.8 ) Pub Date : 2024-02-05 , DOI: 10.1007/s11432-023-3935-8 Ke Xiao , Anna Zhu , Brian Kenji Iwana , Cheng-Lin Liu
In this work, we study character counting in STR from a new viewpoint, giving a principled framework showing that the counting information is involved in both visual decoding and semantic decoding. Based on the principled framework, we propose a novel scene text recognizer with a dual character counting-aware visual and semantic modeling network, where the counting information is fused in both vision and language branches. Experimental results demonstrate the effectiveness of our model.