Scene text recognition (STR) methods have struggled to attain high accur...
Structured text extraction is one of the most valuable and challenging
a...
Recently, end-to-end transformer-based detectors (DETRs) have achieved
r...
A large amount of document data exists in unstructured form such as raw
...
Optical character recognition (OCR) technology has been widely used in
v...
Dominant scene text recognition models commonly contain two building blo...
Natural image matting is a fundamental and challenging computer vision t...
Real-world applications have high demands for semantic segmentation meth...
In this report, we present PP-YOLOE, an industrial state-of-the-art obje...
The better accuracy and efficiency trade-off has been a challenging prob...
In recent years, image recognition applications have developed rapidly. ...
Optical Character Recognition (OCR) systems have been widely used in var...
Recently, research efforts have been concentrated on revealing how
pre-t...
This paper addresses representational block named Hierarchical-Split Blo...
The Optical Character Recognition (OCR) systems have been widely used in...
We present an object detection framework based on PaddlePaddle. We put a...
We present a retrieval based system for landmark retrieval and recogniti...