# Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition

arXiv: https://arxiv.org/abs/2602.03913 · HTML: https://mlsanity.com/paper/2602.03913/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [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)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition](https://mlsanity.com/paper/2003.06606/) (2020)
- [On-the-fly Modulation for Balanced Multimodal Learning](https://mlsanity.com/paper/2410.11582/) (2024)
- [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021)
- [Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning](https://mlsanity.com/paper/2309.01083/) (2023)
- [DenseRAN for Offline Handwritten Chinese Character Recognition](https://mlsanity.com/paper/1808.04134/) (2018)
- [Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark](https://mlsanity.com/paper/1606.05763/) (2016)
- [Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition](https://mlsanity.com/paper/1702.07975/) (2017)
- [RZCR: Zero-shot Character Recognition via Radical-based Reasoning](https://mlsanity.com/paper/2207.05842/) (2022)
- [Chinese Character Recognition with Radical-Structured Stroke Trees](https://mlsanity.com/paper/2211.13518/) (2022)
- [High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps](https://mlsanity.com/paper/1505.04925/) (2015)
- [Template-Instance Loss for Offline Handwritten Chinese Character Recognition](https://mlsanity.com/paper/1910.05545/) (2019)
- [HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition](https://mlsanity.com/paper/2403.13761/) (2024)
- [STAR: Zero-Shot Chinese Character Recognition with Stroke- and Radical-Level Decompositions](https://mlsanity.com/paper/2210.08490/) (2022)
- [Improving Chinese Character Representation with Formation Tree](https://mlsanity.com/paper/2404.12693/) (2024)

## Abstract (arXiv)

Zero-shot Handwritten Chinese Character Recognition (HCCR) aims to recognize unseen characters by leveraging radical-based semantic compositions. However, existing approaches often treat characters as flat radical sequences, neglecting the hierarchical topology and the uneven information density of different components. To address these limitations, we propose an Entropy-Aware Structural Alignment Network that bridges the visual-semantic gap through information-theoretic modeling. First, we introduce an Information Entropy Prior to dynamically modulate positional embeddings via multiplicative interaction, acting as a saliency detector that prioritizes discriminative roots over ubiquitous components. Second, we construct a Dual-View Radical Tree to extract multi-granularity structural features, which are integrated via an adaptive Sigmoid-based gating network to encode both global layout and local spatial roles. Finally, a Top-K Semantic Feature Fusion mechanism is devised to augment the decoding process by utilizing the centroid of semantic neighbors, effectively rectifying visual ambiguities through feature-level consensus. Extensive experiments demonstrate that our method establishes new state-of-the-art performance, achieving an accuracy of 55.04% on the ICDAR 2013 dataset (m=1500), significantly outperforming existing CLIP-based baselines in the challenging zero-shot setting. Furthermore, the framework exhibits exceptional data efficiency, demonstrating rapid adaptability with minimal support samples, achieving 92.41% accuracy with only one support sample per class.