AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

Yinsheng Yao, Yan Liu, Chen Ye

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use raw Wild images instead of processed Origin images (ablation)Qwen3-VL-235B-Instruct · HCSU discriminationaccuracy: 29.95 -> 34.22Improved
Use expert descriptions instead of random ones (Bei) (ablation)Qwen3-VL-235B-Instruct · HCSU discrimination (Bei)accuracy: 30.93 -> 34.10Improved
Use expert descriptions instead of GPT-generated ones (Tie) (ablation)Qwen3-VL-235B-Instruct · HCSU discrimination (Tie)accuracy: 26.74 -> 26.40No clear effect
Use expert descriptions instead of random ones (Tie) (ablation)Qwen3-VL-235B-Instruct · HCSU discrimination (Tie)accuracy: 24.84 -> 26.40Improved
Scale Qwen3-VL from 30B to 235BQwen3-VL · HCSU discriminationavg accuracy: 21.81 -> 30.25Improved
Scale Qwen2.5-VL from 7B to 72BQwen2.5-VL · HCSU discriminationavg accuracy: 20.25 -> 24.93Improved
Evaluate on ink manuscripts (Tie) instead of stone rubbings (Bei)Qwen3-VL-235B-Instruct · HCSU discriminationaccuracy: 34.10 -> 26.40Hurt
Resize Wild images instead of raw (ablation)Qwen3-VL-235B-Instruct · HCSU discriminationaccuracy: 34.22 -> 31.40Hurt
Image condition (raw vs resized vs processed) (ablation)Qwen3-VL-235B-Instruct · HCSU generationBERTScore: 6.94-6.96No clear effect
Go from 1-shot to 2-shot in aesthetic description prompts (ablation)Qwen3-VL-235B probe · HCSU description generationTerminology: +0.33Improved
Best discrimination model vs best generation modelDoubao-1.5-Vision-Pro vs GPT-5.2 · HCSUdiscrimination vs richness: 37.29 vs 34.58 acc; Rich. -1.46 vs +0.82 (Bei)Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy