# Template-Instance Loss for Offline Handwritten Chinese Character Recognition

arXiv: https://arxiv.org/abs/1910.05545 · HTML: https://mlsanity.com/paper/1910.05545/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2019.

## Built on by (most cited first, 9 of 9)

- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [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)
- [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)
- [CALText: Contextual Attention Localization for Offline Handwritten Text](https://mlsanity.com/paper/2111.03952/) (2021)
- [SAN: Structure-Aware Network for Complex and Long-tailed Chinese Text Recognition](https://mlsanity.com/paper/2411.06381/) (2024)
- [Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning](https://mlsanity.com/paper/2505.24837/) (2025)
- [Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition](https://mlsanity.com/paper/2602.03913/) (2026)

## Abstract (arXiv)

The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed and infrequent pen lifting) makes strokes and even characters connected together in a flowing manner. In this paper, we propose the template and instance loss functions for the relevant machine learning tasks in offline handwritten Chinese character recognition. First, the character template is designed to deal with the intrinsic similarities among Chinese characters. Second, the instance loss can reduce category variance according to classification difficulty, giving a large penalty to the outlier instance of handwritten Chinese character. Trained with the new loss functions using our deep network architecture HCCR14Layer model consisting of simple layers, our extensive experiments show that it yields state-of-the-art performance and beyond for offline HCCR.