Transformer is beneficial for image denoising tasks since it can model
l...
This paper explores the multi-scale aggregation strategy for scene text
...
Scene text erasing seeks to erase text contents from scene images and cu...
The document layout analysis (DLA) aims to decompose document images int...
The accuracy of OCR is usually affected by the quality of the input docu...
Texts from scene images typically consist of several characters and exhi...
Image deblurring is a fundamental and challenging low-level vision probl...
Crowd counting aims to count the number of instantaneous people in a cro...
Curve text or arbitrary shape text is very common in real-world scenario...
Crowd counting, i.e., estimation number of pedestrian in crowd images, i...
Crowd counting is one of the core tasks in various surveillance applicat...
Locating actions in long untrimmed videos has been a challenging problem...
This paper introduces a novel rotation-based framework for arbitrary-ori...
We perform fast vehicle detection from traffic surveillance cameras. A n...