AI RESEARCH
A Hybrid Vision Transformer Approach for Mathematical Expression Recognition
arXiv CS.CV
•
ArXi:2603.07929v1 Announce Type: new One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much complicated problem because of its two-dimensional structure and different symbol size. In this paper, we propose using a Hybrid Vision Transformer (HVT) with 2D positional encoding as the encoder to extract the complex relationship between symbols from the image.