55 citations · 60 across the 5 of their papers we have counts for
5 papers
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
Tongkun Guan, Chengyu Lin, Wei Shen +1
Handwritten Mathematical Expression Recognition (HMER) has wide applications in human-machine interaction scenarios, such as digitized education and automated offices. Recently, se…
Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
Tongkun Guan, Wei Shen, Xue Yang +2
Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-sca…
Self-supervised Character-to-Character Distillation for Text Recognition
Tongkun Guan, Wei Shen, Xue Yang +3
When handling complicated text images (e.g., irregular structures, low resolution, heavy occlusion, and uneven illumination), existing supervised text recognition methods are data-…
Self-supervised Implicit Glyph Attention for Text Recognition
Tongkun Guan, Chaochen Gu, Jingzheng Tu +5
The attention mechanism has become the \emph{de facto} module in scene text recognition (STR) methods, due to its capability of extracting character-level representations. These me…
Industrial Scene Text Detection with Refined Feature-attentive Network
Tongkun Guan, Chaochen Gu, Changsheng Lu +4
Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded character structures, and cluttered backgro…