GLASS: Global to Local Attention for Scene-Text Spotting. (arXiv:2208.03364v1 [cs.CV])

In recent years, the dominant paradigm for text spotting is to combine the
tasks of text detection and recognition into a single end-to-end framework.
Under this paradigm, both tasks are accomplished by operating over a shared
global feature map extracted from the input image. Among the main challenges
that end-to-end approaches face is the performance degradation when recognizing
text across scale variations (smaller or larger text), and arbitrary word
rotation angles. In this work, we address these challenges by proposing …

arxiv attention cv global local attention text