Decoding-Time Fusion of OCR and Large Language Models for Traditional Chinese Historical Document Recognition
- 3 August 2026
- book chapter
- Published by Springer Nature
- p. 48-62
Abstract
No abstract availableKeywords
This publication has 13 references indexed in Scilit:
- A large-scale dataset for Chinese historical document recognition and analysisScientific Data, 2025
- OCRBench: on the hidden mystery of OCR in large multimodal modelsScience China Information Sciences, 2024
- TrOCR: Transformer-Based Optical Character Recognition with Pre-trained ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Evaluating Object Hallucination in Large Vision-Language Models2023
- OCR-Free Document Understanding Transformer2022
- Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition2021
- Candidate fusion: Integrating language modelling into a sequence-to-sequence handwritten word recognition architecturePattern Recognition, 2021
- Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization2020
- ICDAR2017 Competition on Post-OCR Text Correction2017
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016