Due to the flexible representation of arbitrary-shaped scene text and si...
Document dewarping from a distorted camera-captured image is of great va...
Structured text extraction is one of the most valuable and challenging
a...
Transformers achieve promising performance in document understanding bec...
In this paper, we present StrucTexTv2, an effective document image
pre-t...
Table structure recognition is a crucial part of document image analysis...
Typical text spotters follow the two-stage spotting strategy: detect the...
In this paper, we present a model pretraining technique, named MaskOCR, ...
Structured text understanding on Visually Rich Documents (VRDs) is a cru...
The reading of arbitrarily-shaped text has received increasing research
...
Fast appearance variations and the distractions of similar objects are t...
Scene text image contains two levels of contents: visual texture and sem...
Video text detection is considered as one of the most difficult tasks in...
Detecting scene text of arbitrary shapes has been a challenging task ove...
In this paper, we are interested in editing text in natural images, whic...
Previous scene text detection methods have progressed substantially over...
Most text detection methods hypothesize texts are horizontal or
multi-or...
Reading text from images remains challenging due to multi-orientation,
p...
Imagery texts are usually organized as a hierarchy of several visual
ele...
In this paper, we propose a novel approach for text detec- tion in natur...
With the rapid increase of transnational communication and cooperation,
...