-
Focusing Attention: Towards Accurate Text Recognition in Natural Images
Scene text recognition has been a hot research topic in computer vision ...
read it
-
A Multi-Object Rectified Attention Network for Scene Text Recognition
Irregular text is widely used. However, it is considerably difficult to ...
read it
-
Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
Text segmentation is a prerequisite in many real-world text-related task...
read it
-
Double Supervised Network with Attention Mechanism for Scene Text Recognition
In this paper, we propose Double Supervised Network with Attention Mecha...
read it
-
Causal Attention for Vision-Language Tasks
We present a novel attention mechanism: Causal Attention (CATT), to remo...
read it
-
Not All Attention Is Needed: Gated Attention Network for Sequence Data
Although deep neural networks generally have fixed network structures, t...
read it
-
Focus-Enhanced Scene Text Recognition with Deformable Convolutions
Recently, scene text recognition methods based on deep learning have spr...
read it
Gaussian Constrained Attention Network for Scene Text Recognition
Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we argue that the existing attention mechanism faces the problem of attention diffusion, in which the model may not focus on a certain character area. In this paper, we propose Gaussian Constrained Attention Network to deal with this problem. It is a 2D attention-based method integrated with a novel Gaussian Constrained Refinement Module, which predicts an additional Gaussian mask to refine the attention weights. Different from adopting an additional supervision on the attention weights simply, our proposed method introduces an explicit refinement. In this way, the attention weights will be more concentrated and the attention-based recognition network achieves better performance. The proposed Gaussian Constrained Refinement Module is flexible and can be applied to existing attention-based methods directly. The experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. Our code has been available at https://github.com/Pay20Y/GCAN.
READ FULL TEXT
Comments
There are no comments yet.