# A3S: Adversarial learning of semantic representations for Scene-Text Spotting

arXiv: https://arxiv.org/abs/2302.10641 · HTML: https://mlsanity.com/paper/2302.10641/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 21 Feb 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019](https://mlsanity.com/paper/1907.00945/) (2019)
- [TextBoxes: A Fast Text Detector with a Single Deep Neural Network](https://mlsanity.com/paper/1611.06779/) (2016)
- [Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting](https://mlsanity.com/paper/2007.09482/) (2020)
- [FOTS: Fast Oriented Text Spotting with a Unified Network](https://mlsanity.com/paper/1801.01671/) (2018)
- [ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting](https://mlsanity.com/paper/2105.03620/) (2021)
- [SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition](https://mlsanity.com/paper/2203.10209/) (2022)
- [Text Spotting Transformers](https://mlsanity.com/paper/2204.01918/) (2022)
- [Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1707.03985/) (2017)
- [MANGO: A Mask Attention Guided One-Stage Scene Text Spotter](https://mlsanity.com/paper/2012.04350/) (2020)
- [PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network](https://mlsanity.com/paper/2104.05458/) (2021)
- [GLASS: Global to Local Attention for Scene-Text Spotting](https://mlsanity.com/paper/2208.03364/) (2022)
- [Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition](https://mlsanity.com/paper/2111.12351/) (2021)

## Built on by (most cited first, 6 of 6)

- [DTrOCR: Decoder-only Transformer for Optical Character Recognition](https://mlsanity.com/paper/2308.15996/) (2023)
- [LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding](https://mlsanity.com/paper/2403.14252/) (2024)
- [DiffusionSTR: Diffusion Model for Scene Text Recognition](https://mlsanity.com/paper/2306.16707/) (2023)
- [RL-LOGO: Deep Reinforcement Learning Localization for Logo Recognition](https://mlsanity.com/paper/2312.16792/) (2023)
- [JSTR: Judgment Improves Scene Text Recognition](https://mlsanity.com/paper/2404.05967/) (2024)
- [JaPOC: Japanese Post-OCR Correction Benchmark using Vouchers](https://mlsanity.com/paper/2409.19948/) (2024)

## Abstract (arXiv)

Scene-text spotting is a task that predicts a text area on natural scene images and recognizes its text characters simultaneously. It has attracted much attention in recent years due to its wide applications. Existing research has mainly focused on improving text region detection, not text recognition. Thus, while detection accuracy is improved, the end-to-end accuracy is insufficient. Texts in natural scene images tend to not be a random string of characters but a meaningful string of characters, a word. Therefore, we propose adversarial learning of semantic representations for scene text spotting (A3S) to improve end-to-end accuracy, including text recognition. A3S simultaneously predicts semantic features in the detected text area instead of only performing text recognition based on existing visual features. Experimental results on publicly available datasets show that the proposed method achieves better accuracy than other methods.