Scholarlink

<p>With three millennia of evolution history, ancient Chinese characters present unique challenges for intelligent recognition systems due to severe degradation and stylistic variations, causing notable intra-class variation and reduced inter-class separability. To address this, we propose a novel framework with two key components: a local content transformation (LCT) module enhancing salient regions through learnable spatial attention weights, and a local correlation reasoning (LCR) module employing graph convolutional networks (GCNs) to model patch-wise spatial-semantic dependencies via Transformer-derived attention maps. Experiments on the MACT benchmark show it achieves state-of-the-art performance with a 2.02% top-1 accuracy improvement compared to existing methods. The proposed architecture exhibits particular robustness in handling degraded samples and distinguishing visually similar character classes, showing substantial potential for applications in archeological documentation, digital paleography, and intelligent cultural heritage preservation systems. Code is available at <a href="https://github.com/wtq123-git/AttGraph">https://github.com/wtq123-git/AttGraph</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AttGraph disentangling confusable ancient Chinese characters via component-correlation synergy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月5日

查看全文
  • Kaili Wang,
  • Tianquan Wu,
  • Yuanlin Shi,
  • Chen Chen

摘要

With three millennia of evolution history, ancient Chinese characters present unique challenges for intelligent recognition systems due to severe degradation and stylistic variations, causing notable intra-class variation and reduced inter-class separability. To address this, we propose a novel framework with two key components: a local content transformation (LCT) module enhancing salient regions through learnable spatial attention weights, and a local correlation reasoning (LCR) module employing graph convolutional networks (GCNs) to model patch-wise spatial-semantic dependencies via Transformer-derived attention maps. Experiments on the MACT benchmark show it achieves state-of-the-art performance with a 2.02% top-1 accuracy improvement compared to existing methods. The proposed architecture exhibits particular robustness in handling degraded samples and distinguishing visually similar character classes, showing substantial potential for applications in archeological documentation, digital paleography, and intelligent cultural heritage preservation systems. Code is available at https://github.com/wtq123-git/AttGraph.