Puzzle Pieces Picker: Deciphering Ancient Chinese Characters with Radical Reconstruction
Not on the map. Why?
Abstract (arXiv)
Oracle Bone Inscriptions is one of the oldest existing forms of writing in the world. However, due to the great antiquity of the era, a large number of Oracle Bone Inscriptions (OBI) remain undeciphered, making it one of the global challenges in the field of paleography today. This paper introduces a novel approach, namely Puzzle Pieces Picker (P3), to decipher these enigmatic characters through radical reconstruction. We deconstruct OBI into foundational strokes and radicals, then employ a Transformer model to reconstruct them into their modern (conterpart)textcolorbluecounterparts, offering a groundbreaking solution to ancient script analysis. To further this endeavor, a new Ancient Chinese Character Puzzles (ACCP) dataset was developed, comprising an extensive collection of character images from seven key historical stages, annotated with detailed radical sequences. The experiments have showcased considerable promising insights, underscoring the potential and effectiveness of our approach in deciphering the intricacies of ancient Chinese scripts. Through this novel dataset and methodology, we aim to bridge the gap between traditional philology and modern document analysis techniques, offering new insights into the rich history of Chinese linguistic heritage.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 5 Jun 2024.
Builds on
16 of 37 references.
References · 16
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2023Segment Anythingcited by 8,158
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2015SSD: Single Shot MultiBox Detectorcited by 3,125
- 2015Fast R-CNNcited by 2,930
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2020On Layer Normalization in the Transformer Architecturecited by 906
- 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
- 2021SPTS: Single-Point Text Spottingcited by 45
- 2018DenseRAN for Offline Handwritten Chinese Character Recognitioncited by 24
4 more
- 2024An open dataset for oracle bone script recognition and deciphermentcited by 18
- 2022Unsupervised Structure-Texture Separation Network for Oracle Character Recognitioncited by 15
- 2024An open dataset for the evolution of oracle bone characters: EVOBCcited by 15
- 2023Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotationscited by 10
Built on by
Citing papers per year: 2024: 1; 2025: 2; 2026: 5.
8 papers.
- 2025MCCD: A Multi-Attribute Chinese Calligraphy Character Dataset Annotated with Script Styles, Dynasties, and Calligrapherscited by 3
- 2025Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMscited by 3
- 2024A Cross-Font Image Retrieval Network for Recognizing Undeciphered Oracle Bone Inscriptionscited by 1
- 2026Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentationcited by 1
- 2026Towards Computational Chinese Paleographycited by 0
- 2026OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-trainingcited by 0
- 2026AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learningcited by 0
- 2026JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesiscited by 0
- 2026JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesis12 Aug 2026
- 2026AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning20 Jul 2026
- 2026OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training24 Jun 2026
- 2026Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation8 Apr 2026
- 2026Towards Computational Chinese Paleography11 Jan 2026
- 2025Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMs13 Aug 2025
- 2025MCCD: A Multi-Attribute Chinese Calligraphy Character Dataset Annotated with Script Styles, Dynasties, and Calligraphers9 Jul 2025
- 2024A Cross-Font Image Retrieval Network for Recognizing Undeciphered Oracle Bone Inscriptions10 Sep 2024