# SEE: Towards Semi-Supervised End-to-End Scene Text Recognition

arXiv: https://arxiv.org/abs/1712.05404 · HTML: https://mlsanity.com/paper/1712.05404/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2017.

## Built on by (most cited first, 12 of 12)

- [SPTS v2: Single-Point Scene Text Spotting](https://mlsanity.com/paper/2301.01635/) (2023)
- [SPTS: Single-Point Text Spotting](https://mlsanity.com/paper/2112.07917/) (2021)
- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer](https://mlsanity.com/paper/2202.05508/) (2022)
- [Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning](https://mlsanity.com/paper/2207.11934/) (2022)
- [Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis](https://mlsanity.com/paper/2310.17674/) (2023)
- [Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links](https://mlsanity.com/paper/2103.00785/) (2021)
- [DocReader: Bounding-Box Free Training of a Document Information Extraction Model](https://mlsanity.com/paper/2105.04313/) (2021)
- [Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting](https://mlsanity.com/paper/2207.06694/) (2022)
- [Image-free multi-character recognition](https://mlsanity.com/paper/2112.10587/) (2021)
- [Sim2Real Docs: Domain Randomization for Documents in Natural Scenes using Ray-traced Rendering](https://mlsanity.com/paper/2112.09220/) (2021)
- [SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting](https://mlsanity.com/paper/2609.07081/) (2026)

## Abstract (arXiv)

Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In recent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Most existing works consist of multiple deep neural networks and several pre-processing steps. In contrast to this, we propose to use a single deep neural network, that learns to detect and recognize text from natural images, in a semi-supervised way. SEE is a network that integrates and jointly learns a spatial transformer network, which can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We introduce the idea behind our novel approach and show its feasibility, by performing a range of experiments on standard benchmark datasets, where we achieve competitive results.