The basic principle of the patch-matching based style transfer is to
sub...
Catastrophic forgetting of previous knowledge is a critical issue in
con...
Knowledge distillation learns a lightweight student model that mimics a
...
Expandable networks have demonstrated their advantages in dealing with
c...
End-to-end text spotting has attached great attention recently due to it...
Open Set Recognition (OSR) has been an emerging topic. Besides recognizi...
In the SSLAD-Track 3B challenge on continual learning, we propose the me...
Few-shot learning (FSL) aims to learn models that generalize to novel cl...
Text recognition is a popular topic for its broad applications. In this ...
Table structure recognition is a challenging task due to the various
str...
Document layout analysis is crucial for understanding document structure...
Recently end-to-end scene text spotting has become a popular research to...
In 2D+3D facial expression recognition (FER), existing methods generate
...
In real applications, object detectors based on deep networks still face...
Scene text recognition (STR) is still a hot research topic in computer v...
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes ...
Arbitrary text appearance poses a great challenge in scene text recognit...
In object recognition applications, object images usually appear with
di...
Recurrent neural network (RNN) has been widely studied in sequence learn...
Many approaches have recently been proposed to detect irregular scene te...
Temporal action localization is an important yet challenging research to...
Fine-grained image recognition has been a hot research topic in computer...
This paper proposes an unified framework for efficiently spotting scene ...
This paper proposes a segregated temporal assembly recurrent (STAR) netw...
We consider the scene text recognition problem under the attention-based...
Recognizing text from natural images is still a hot research topic in
co...