… MORAN framework to recognize irregular scene text. The framework contains a multi-object
rectification network (MORN) and an attention-based sequence recognition network (ASRN). …

… networks for sequence modeling. In this work, we propose a simple yet strong approach for
scene text recognition. … -dimensional CNN features to an attention-based sequence decoder …

… attention network for unconstrained scene text recognition. Different from the recurrent-based
attention … deal with long-term dependencies of character sequences. • We show that spatial …

… In this work, we proposed an effective parts attention network (EPAN) for scene text
recognition. The proposed model samples informative parts of text from a 2D feature map, and …

… of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention
Network (SGBANet) to recognize the texts in scene … the scene text with the Balanced Attention …

… mechanism into an alignment module and a decoupled text decoder, and … network (DAN)
for text recognition. As shown in Figure 1 (b), compared with traditional attentional scene text …

… In this paper, we proposed a two-level rectification attention network for scene text recognition.
The two-level rectification network combined geometry-level and pixel-level methods, …

… attention network for arbitrary-orientation scene text recognition, which consists of a dynamic
log-polar transformer and a sequence recognition network. … on the scene text recognition. …

… The main contributions are summarized as follows: 1) We define and explore the
problem of attention diffusion in scene text recognition, where the attention weights are not …

… visual attention (VA) sequentially, which bounds the attention … Moreover, the utilization of the
attention process is limited by … -based attention network for text recognition that performs the …