# Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition

arXiv: https://arxiv.org/abs/2207.08191 · HTML: https://mlsanity.com/paper/2207.08191/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 17 Jul 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [Deep Learning Based Text Classification: A Comprehensive Review](https://mlsanity.com/paper/2004.03705/) (2020)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information](https://mlsanity.com/paper/2106.16038/) (2021)
- [Analogical Reasoning on Chinese Morphological and Semantic Relations](https://mlsanity.com/paper/1805.06504/) (2018)
- [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021)
- [DenseRAN for Offline Handwritten Chinese Character Recognition](https://mlsanity.com/paper/1808.04134/) (2018)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding](https://mlsanity.com/paper/2012.08687/) (2020)
- [Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark](https://mlsanity.com/paper/1606.05763/) (2016)
- [MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition](https://mlsanity.com/paper/2107.05418/) (2021)
- [GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph](https://mlsanity.com/paper/2107.00395/) (2021)
- [MFE-NER: Multi-feature Fusion Embedding for Chinese Named Entity Recognition](https://mlsanity.com/paper/2109.07877/) (2021)

## Built on by (most cited first, 3 of 3)

- [Chinese Character Recognition with Radical-Structured Stroke Trees](https://mlsanity.com/paper/2211.13518/) (2022)
- [STAR: Zero-Shot Chinese Character Recognition with Stroke- and Radical-Level Decompositions](https://mlsanity.com/paper/2210.08490/) (2022)
- [Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning](https://mlsanity.com/paper/2505.24837/) (2025)

## Abstract (arXiv)

Chinese characters carry a wealth of morphological and semantic information; therefore, the semantic enhancement of the morphology of Chinese characters has drawn significant attention. The previous methods were intended to directly extract information from a whole Chinese character image, which usually cannot capture both global and local information simultaneously. In this paper, we develop a stroke-based autoencoder(SAE), to model the sophisticated morphology of Chinese characters with the self-supervised method. Following its canonical writing order, we first represent a Chinese character as a series of stroke images with a fixed writing order, and then our SAE model is trained to reconstruct this stroke image sequence. This pre-trained SAE model can predict the stroke image series for unseen characters, as long as their strokes or radicals appeared in the training set. We have designed two contrasting SAE architectures on different forms of stroke images. One is fine-tuned on existing stroke-based method for zero-shot recognition of handwritten Chinese characters, and the other is applied to enrich the Chinese word embeddings from their morphological features. The experimental results validate that after pre-training, our SAE architecture outperforms other existing methods in zero-shot recognition and enhances the representation of Chinese characters with their abundant morphological and semantic information.