Despite the rapid advancement of unsupervised learning in visual
represe...
Open-world instance-level scene understanding aims to locate and recogni...
Precise and controllable image editing is a challenging task that has
at...
Most existing scene text detectors require large-scale training data whi...
Open-vocabulary scene understanding aims to localize and recognize unsee...
Scene text recognition has attracted increasing interest in recent years...
This report presents our winner solution to ECCV 2022 challenge on
Out-o...
Most existing scene text detectors focus on detecting characters or word...
State-of-the-art document dewarping techniques learn to predict 3-dimens...
Recently, Vision-Language Pre-training (VLP) techniques have greatly
ben...
Leveraging the advances of natural language processing, most recent scen...
Detection and recognition of scene texts of arbitrary shapes remain a gr...
Recent adversarial learning research has achieved very impressive progre...
State-of-the-art scene text detection techniques predict quadrilateral b...
This paper presents a scene text detection technique that exploits
boots...
The requirement of large amounts of annotated images has become one gran...