We exploit the potential of the large-scale Contrastive Language-Image
P...
In recent years, end-to-end scene text spotting approaches are evolving ...
Conditional spatial queries are recently introduced into DEtection
TRans...
We introduce the notion of point affiliation into feature upsampling. By...
Scene text removal (STR) aims at replacing text strokes in natural scene...
Text recognition in the wild is a long-standing problem in computer visi...
Structured text extraction is one of the most valuable and challenging
a...
Large models have recently played a dominant role in natural language
pr...
Reading seal title text is a challenging task due to the variable shapes...
Given a command, humans can directly execute the action after thinking o...
The recent large-scale Contrastive Language-Image Pretraining (CLIP) mod...
In recent years, large-scale models have demonstrated state-of-the-art
p...
End-to-end scene text spotting has made significant progress due to its
...
Although online handwriting verification has made great progress recentl...
We introduce point affiliation into feature upsampling, a notion that
de...
Handwritten Chinese text recognition (HCTR) has been an active research ...
Text removal has attracted increasingly attention due to its various
app...
The further development of deep neural networks is hampered by the limit...
End-to-end scene text spotting has attracted great attention in recent y...
Almost all scene text spotting (detection and recognition) methods rely ...
With hundreds of thousands of electronic chip components are being
manuf...
End-to-end text-spotting, which aims to integrate detection and recognit...
Text based Visual Question Answering (TextVQA) is a recently raised chal...
Visual Question Answering (VQA) methods have made incredible progress, b...
Scene text detection and recognition has received increasing research
at...
In this work we propose to improve text recognition from a new perspecti...
Omnidirectional scene text detection has received increasing research
at...
Robust text reading from street view images provides valuable informatio...
This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-S...
Scene text in the wild is commonly presented with high variant
character...
In this paper, we propose a novel method, aggregation cross-entropy (ACE...
Evaluation protocols play key role in the developmental progress of text...
A new method is proposed for removing text from natural images. The chal...
Most current detection methods have adopted anchor boxes as regression
r...
In this paper, we propose a refined scene text detector with a novel
Fea...
Detecting incidental scene text is a challenging task because of
multi-o...