DenseBAM-GI：用于HMER的基于注意力增强DenseNet和动量辅助GRU的模型
DenseBAM-GI: Attention Augmented DeneseNet with momentum aided GRU for HMER
AI总结：
提出用于手写数学表达式识别的新型编码器-解码器架构DenseBAM-GI，通过结合BAM和GI-GRU提升识别率并降低计算复杂度与显存需求。
摘要：
识别手写数学表达式（HMER）的任务在数字教育和学术研究领域至关重要。然而，准确确定手写数学表达式中符号的长度和复杂的空间关系十分困难。在本研究中，我们提出了一种用于HMER的新型编码器-解码器架构（DenseBAM-GI），其编码器包含一个瓶颈注意力模块（BAM）以改善特征表示，解码器包含一个带有额外门控的门控输入-GRU（GI-GRU）单元，使解码长且复杂的表达式更加容易。所提出的模型是一种高效且轻量级的架构，在表达式识别率（exprate）方面具有与最先进模型相当的性能。在CROHME 2014、2016和2019数据集上，它在top 1、2和3错误准确率方面也表现更好。DenseBAM-GI在CROHME 2019数据集上取得了所有模型中最佳的exprate。重要的是，这些成功是在计算复杂性下降和GPU内存需求减少的情况下实现的。
英文摘要：
The task of recognising Handwritten Mathematical Expressions (HMER) is crucial in the fields of digital education and scholarly research. However, it is difficult to accurately determine the length and complex spatial relationships among symbols in handwritten mathematical expressions. In this study, we present a novel encoder-decoder architecture (DenseBAM-GI) for HMER, where the encoder has a Bottleneck Attention Module (BAM) to improve feature representation and the decoder has a Gated Input-GRU (GI-GRU) unit with an extra gate to make decoding long and complex expressions easier. The proposed model is an efficient and lightweight architecture with performance equivalent to state-of-the-art models in terms of Expression Recognition Rate (exprate). It also performs better in terms of top 1, 2, and 3 error accuracy across the CROHME 2014, 2016, and 2019 datasets. DenseBAM-GI achieves the best exprate among all models on the CROHME 2019 dataset. Importantly, these successes are accomplished with a drop in the complexity of the calculation and a reduction in the need for GPU memory.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
