Latest Research in Document Transcription Forensics

Top Research Topics in Document Transcription Forensics

• Computer Vision and Pattern Recognition — 17 papers
• Handwritten Text Recognition Techniques — 10 papers
• Computation and Language — 5 papers
• Artificial Intelligence — 2 papers
• Authorship Attribution and Profiling — 1 papers
• Machine Learning — 1 papers
• Advanced Image and Video Retrieval Techniques — 1 papers
• Cultural Heritage Management and Preservation — 1 papers

Highest-Cited Papers

1. JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesis
2. Research on Lightweight Stylistic Features for Author Verification
3. Library spine text detection based on SAM and CFA
4. TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents
5. Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition
6. LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
7. Robust recognition of Tamil inscription letters using a hybrid model combining recurrent neural networks, graph neural networks, and attention mechanisms
8. CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document Understanding
9. MBG-PSENet: A PSENet-Based Model for Dense Text Detection in Customs Declarations
10. Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion
11. Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription
12. HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
13. Enhancing scene text super-resolution via dense residual reconstruction and asymmetric recurrent modeling
14. DTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection
15. Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press
16. A machine-readable catalogue of the Tsiolkovsky papers (fond 555, Archive of the Russian Academy of Sciences), and a way to measure how well its handwriting can be read
17. BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models
18. Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction
19. Large language models for OCR in cultural heritage: a comparative study on Slovene Folkloristic texts
20. MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing

Sub-Regions

• Computer Vision and Pattern Recognition — 27 papers
• Handwritten Text Recognition Techniques — 6 papers
• Authorship Attribution and Profiling — 5 papers
• Diverse Scientific and Economic Studies — 2 papers
• Robotics and Sensor-Based Localization — 2 papers
• Computation and Language — 1 papers