Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917364690321408 |
|---|---|
| author | Zheng, Chen Lai, Yuxuan Lu, Haoyang Ma, Wentao Yang, Jitao Wang, Jian |
| author_facet | Zheng, Chen Lai, Yuxuan Lu, Haoyang Ma, Wentao Yang, Jitao Wang, Jian |
| contents | The handwriting of Chinese characters is a fundamental aspect of learning the Chinese language. Previous automated assessment methods often framed scoring as a regression problem. However, this score-only feedback lacks actionable guidance, which limits its effectiveness in helping learners improve their handwriting skills. In this paper, we leverage vision-language models (VLMs) to analyze the quality of handwritten Chinese characters and generate multi-level feedback. Specifically, we investigate two feedback generation tasks: simple grade feedback (Task 1) and enriched, descriptive feedback (Task 2). We explore both low-rank adaptation (LoRA)-based fine-tuning strategies and in-context learning methods to integrate aesthetic assessment knowledge into VLMs. Experimental results show that our approach achieves state-of-the-art performances across multiple evaluation tracks in the CCL 2025 workshop on evaluation of handwritten Chinese character quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26768 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models Zheng, Chen Lai, Yuxuan Lu, Haoyang Ma, Wentao Yang, Jitao Wang, Jian Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language The handwriting of Chinese characters is a fundamental aspect of learning the Chinese language. Previous automated assessment methods often framed scoring as a regression problem. However, this score-only feedback lacks actionable guidance, which limits its effectiveness in helping learners improve their handwriting skills. In this paper, we leverage vision-language models (VLMs) to analyze the quality of handwritten Chinese characters and generate multi-level feedback. Specifically, we investigate two feedback generation tasks: simple grade feedback (Task 1) and enriched, descriptive feedback (Task 2). We explore both low-rank adaptation (LoRA)-based fine-tuning strategies and in-context learning methods to integrate aesthetic assessment knowledge into VLMs. Experimental results show that our approach achieves state-of-the-art performances across multiple evaluation tracks in the CCL 2025 workshop on evaluation of handwritten Chinese character quality. |
| title | Aesthetic Assessment of Chinese Handwritings Based on Vision Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2603.26768 |