Research map / Vision-language and multimodal / Multimodal LLMs
OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography
Caoshuo Li, Zengmao Ding, Xiaobin Hu, Bang Li, Donghao Luo, AndyPian Wu, Chaoyang Wang, Chengjie Wang, Taisong Jin, Seven Shu, Yunsheng Wu, Yongge Liu and 1 more
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-turn dialogue instead of end-to-end (ablation) | OBSUG · RMOBS OBSUG | Component count accuracy (%): 81.03 -> 81.65 | Improved |
| add multi-turn dialogue instead of end-to-end (ablation) | OBSUG · RMOBS OBSUG | mIoU (%): 72.56 -> 72.03 | Hurt |
| add multi-turn dialogue instead of end-to-end (ablation) | OBSUG · RMOBS OBSUG | BLEU-4 holistic: 0.876 -> 0.910 | Improved |
| add Spatial Awareness Reasoning (SAR) (ablation) | OBSUG multi-turn · RMOBS OBSUG | mIoU (%): 72.03 -> 73.94 | Improved |
| add Spatial Awareness Reasoning (SAR) (ablation) | OBSUG multi-turn · RMOBS OBSUG | BLEU-4 radical: 0.865 -> 0.876 | Improved |
| add Spatial Awareness Reasoning (SAR) (ablation) | OBSUG multi-turn · RMOBS OBSUG | Component count accuracy (%): 81.65 -> 82.02 | Improved |
| add GSDS loss (glyph structural constraint) (ablation) | SOVF · RMOBS semantic typography | qualitative concept completeness | Improved |
| add SKST loss weight beta 0.5 instead of 0 (ablation) | SOVF · RMOBS semantic typography | glyph preservation vs semantics | Improved |
| use OracleFusion instead of Word-As-Image | semantic typography · RMOBS semantic typography | CLIPScore: 27.28 -> 28.30 | Improved |
| use OracleFusion instead of Word-As-Image | semantic typography · RMOBS semantic typography | Distance to original glyph: 0.92 -> 0.86 | Improved |
| use OracleFusion instead of Word-As-Image | semantic typography · RMOBS semantic typography | User study glyph maintenance (1-5): 3.44 -> 3.95 | Improved |
Closest papers by meaning
- OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones? (ICLR 2025 · similarity 0.90)
- Making Visual Sense of Oracle Bones for You and Me (CVPR 2024 · similarity 0.88)
- Component-Level Segmentation for Oracle Bone Inscription Decipherment (AAAI 2025 · similarity 0.88)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.86)
- ProtoSnap: Prototype Alignment For Cuneiform Signs (ICLR 2025 · similarity 0.83)
- IF-Font: Ideographic Description Sequence-Following Font Generation (NeurIPS 2024 · similarity 0.82)
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.
