Image de couverture de livre

Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Do, Thao, Tran, Dinh Phu, Vo, An, Kim, Daeyoung
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SAT: Selective Aggregation Transformer for Image Super-Resolution
par: Tran, Dinh Phu, et autres
Publié: (2026)

VSRM: A Robust Mamba-Based Framework for Video Super-Resolution
par: Tran, Dinh Phu, et autres
Publié: (2025)

TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning
par: Kim, Seongah, et autres
Publié: (2026)

Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution
par: Tran, Dinh Phu, et autres
Publié: (2024)

LooComp: Leverage Leave-One-Out Strategy to Encoder-only Transformer for Efficient Query-aware Context Compression
par: Do, Thao, et autres
Publié: (2026)

Improving OCR for Historical Texts of Multiple Languages
par: Westerdijk, Hylke, et autres
Publié: (2025)

olmOCR 2: Unit Test Rewards for Document OCR
par: Poznanski, Jake, et autres
Publié: (2025)

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy
par: Guan, Shuhao, et autres
Publié: (2025)

VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
par: Ju, Jeongho, et autres
Publié: (2024)

RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages
par: Kashid, Harshvivek, et autres
Publié: (2024)

Seeing Straight: Document Orientation Detection for Efficient OCR
par: Goswami, Suranjan, et autres
Publié: (2025)

HATFormer: Historic Handwritten Arabic Text Recognition with Transformers
par: Chan, Adrian, et autres
Publié: (2024)

Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities
par: Levchenko, Maria
Publié: (2025)

Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR
par: Hennara, Khalil, et autres
Publié: (2025)

LungCRCT: Causal Representation based Lung CT Processing for Lung Cancer Treatment
par: Kim, Daeyoung
Publié: (2026)

SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detection
par: Hu, Xingjian, et autres
Publié: (2024)

Confidence-Aware Document OCR Error Detection
par: Hemmer, Arthur, et autres
Publié: (2024)

Trans2Unet: Neural fusion for Nuclei Semantic Segmentation
par: Tran, Dinh-Phu, et autres
Publié: (2024)

Handwriting Recognition in Historical Documents with Multimodal LLM
par: Li, Lucian
Publié: (2024)

FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
par: Tang, Zihan, et autres
Publié: (2026)

CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition
par: Semnani, Sina J., et autres
Publié: (2025)

LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?
par: Ye, Maoyuan, et autres
Publié: (2025)

GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
par: Kargaran, Amir Hossein, et autres
Publié: (2026)

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization
par: Nguyen, Son, et autres
Publié: (2025)

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR
par: Gagnier, Henry, et autres
Publié: (2026)

QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding
par: Le, Binh M., et autres
Publié: (2025)

Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding
par: Al-Homoud, Haneen, et autres
Publié: (2025)

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
par: Zhong, Yufeng, et autres
Publié: (2025)

Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
par: Tran, Minh-Tuan, et autres
Publié: (2024)

Towards Deployable OCR models for Indic languages
par: Mathew, Minesh, et autres
Publié: (2022)

Unified Framework with Consistency across Modalities for Human Activity Recognition
par: Tran, Tuyen, et autres
Publié: (2024)

Multi-LLM Collaborative Caption Generation in Scientific Documents
par: Kim, Jaeyoung, et autres
Publié: (2025)

OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
par: Liu, Yuliang, et autres
Publié: (2023)

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
par: Fu, Zihao, et autres
Publié: (2025)

Time-Efficient and Identity-Consistent Virtual Try-On Using A Variant of Altered Diffusion Models
par: Dam, Phuong, et autres
Publié: (2024)

SignBart -- New approach with the skeleton sequence for Isolated Sign language Recognition
par: Nguyen, Tinh, et autres
Publié: (2025)

TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems
par: Vo, Khang H. N., et autres
Publié: (2025)

MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
par: Xu, Bangrui, et autres
Publié: (2026)

LightHCG: a Lightweight yet powerful HSIC Disentanglement based Causal Glaucoma Detection Model framework
par: Kim, Daeyoung
Publié: (2025)

ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding
par: Abdallah, Abdelrahman, et autres
Publié: (2024)