Yu-Gang Jiang, Chenxia Li, Zhineng Chen, Caiyan Jia, Yuning Du, Yongkun Du, Xiaoting Yin, Tianlun Zheng
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In this study, we propose a Single Visual model for Scene Text recognition within the patch-wise image tokenization framework, which dispenses with the sequential modeling entirely. The method, termed SVTR, firstly decomposes an image text into small patches named character components. Afterward, hierarchical stages are recurrently carried out by component-level mixing, merging and/or combining. Global and local mixing blocks are devised to perceive the inter-character and intra-character patterns, leading to a multi-grained character component perception. Thus, characters are recognized by a simple linear prediction. Experimental results on both English and Chinese scene text recognition tasks demonstrate the effectiveness of SVTR. SVTR-L (Large) achieves highly competitive accuracy in English and outperforms existing methods by a large margin in Chinese, while running faster. In addition, SVTR-T (Tiny) is an effective and much smaller model, which shows appealing speed at inference. The code is publicly available at https://github.com/PaddlePaddle/PaddleOCR.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.00159")
get_code_for_paper("2205.00159")
have("2205.00159")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.00159.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.00159)
Connect an agent — have() is free.