Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition

By Hui Li, Peng Wang, Chunhua Shen, Guyu Zhang. AAAI Conference on Artificial Intelligence, 2018

448 citations recorded by the source corpus.

Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion. Most existing approaches rely heavily on sophisticated model designs and/or extra fine-grained annotations, which, to some extent, increase the difficulty in algorithm implementation and data collection. In this work, we propose an easy-to-implement strong baseline for irregular scene text recognition, using offthe-shelf neural network components and only word-level annotations. It is composed of a 31-layer ResNet, an LSTMbased encoder-decoder framework and a 2-dimensional attention module. Despite its simplicity, the proposed method is robust. It achieves state-of-the-art performance on irregular text recognition benchmarks and comparable results on regular text datasets. The code will be released.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e7e4ecbb3ac6f69688eed29451bd8b7bf4fdf316

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Accurate Scene Text Recognition With Semantic Reasoning Networks (2020, unknown): “[20] (SAR) ResNet,90K+ST word 91.”
RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition (2020, methodology): “Since then, many variants [6,24,54] were emerged with improvements in recognition quality.”
MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining (2022, background): “Decoder pretraining for text recognition The attention decoder [43; 26; 50] in some sense is able to learn the text relation from the training data.”
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition (2021, unknown): “…recognition (VR) task and perform character-level recognition on input images, including visual-text sequence translation-based methods (Yang et al. 2017; Shi et al. 2018; Baek et al. 2019; Li et al. 2019; Litman et al. 2020) and semantic segmentation-based methods (Liao et al. 2019; Wan et 2020a).”
Scene Text Detection and Recognition: The Deep Learning Era (2018, unknown): “been verified in (Li et al., 2019).”
Decoupled Attention Network for Text Recognition (2019, methodology): “(Li et al. 2019) proposed a simple and effective model using 2D attention mechanism.”