Attention Guidance Mechanism for Handwritten Mathematical Expression Recognition

arXiv:2403.01756v1 Announce Type: new
Abstract: Handwritten mathematical expression recognition (HMER) is challenging in OCR tasks due to the complex layouts of mathematical expressions, suffering from issues including over-parsing and under-parsing. To solve these, previous methods utilize historical attention weights to improve the attention mechanism. However, this approach has limitations in addressing under-parsing since it cannot correct the erroneous attention on image regions that should be parsed at subsequent decoding steps. When this happens, the attention module incorporates future context into …

abstract arxiv attention cs.cv guidance limitations ocr parsing recognition solve tasks type