Scholarlink

Handwritten Mathematical Expression Recognition (HMER) is crucial for enhancing human-machine interaction in domains such as digitized education and automated document processing. While existing transformer-based methods employ coverage mechanisms to capture context, they often still lose critical cues that a human could quickly correct. To address this, we propose Mask CoMER, a two-stage training approach that combines a novel Masked Language Model Pretraining objective with stochastic depth regularization. This method enhances contextual understanding and mitigates information loss, leading to improved recognition accuracy. Experiments on the CROHME 2014, 2016, and 2019 datasets demonstrate that Mask CoMER achieves state-of-the-art ExpRates of 64.56%, 63.03%, and 65.22%, respectively. These results outperform the baseline CoMER by up to 5% and surpass the previous SOTA by nearly 2%. These results underscore the robustness and effectiveness of our approach for HMER tasks  \(^{1}\) .( \(^{1}\) The code is available at  GitHub )

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

Mask CoMER: Enhancing Handwritten Mathematical Expression Recognition with Masked Language Pretraining and Regularization

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nam Van Hai Phan,
  • Khoa Minh Nguyen,
  • Trung Thanh Nguyen,
  • Trung Thanh Pham,
  • Phuong-Nam Tran,
  • Duc Ngoc Minh Dang

摘要

Handwritten Mathematical Expression Recognition (HMER) is crucial for enhancing human-machine interaction in domains such as digitized education and automated document processing. While existing transformer-based methods employ coverage mechanisms to capture context, they often still lose critical cues that a human could quickly correct. To address this, we propose Mask CoMER, a two-stage training approach that combines a novel Masked Language Model Pretraining objective with stochastic depth regularization. This method enhances contextual understanding and mitigates information loss, leading to improved recognition accuracy. Experiments on the CROHME 2014, 2016, and 2019 datasets demonstrate that Mask CoMER achieves state-of-the-art ExpRates of 64.56%, 63.03%, and 65.22%, respectively. These results outperform the baseline CoMER by up to 5% and surpass the previous SOTA by nearly 2%. These results underscore the robustness and effectiveness of our approach for HMER tasks  \(^{1}\) .( \(^{1}\) The code is available at  GitHub )