No article text was recorded for this version.
OCR error propagation (upstream extraction dependency)
Version 1 of 161 papers70 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DocVLM: Make Your VLM an Efficient Reader
- Blog: Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship
- Blog: HRDoc: Dataset and Baseline Method toward Hierarchical Reconstruction of Document Structures
- Blog: TableLab: An Interactive Table Extraction System with Adaptive Deep Learning
- Blog: ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents
- Blog: EKTVQA: Generalized Use of External Knowledge to Empower Scene Text in Text-VQA
- Blog: An End-to-End OCR Text Re-organization Sequence Learning for Rich-Text Detail Image Comprehension
- Blog: Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
- Blog: DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
- Blog: StructuralLM: Structural Pre-training for Form Understanding
- Blog: MUST-VQA: MUltilingual Scene-text VQA
- Blog: Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models
- Blog: Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding
- Blog: PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction
- Blog: Generative Compositor for Few-Shot Visual Information Extraction
- Blog: Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance
- Blog: GlyphSR: A Simple Glyph-Aware Framework for Scene Text Image Super-Resolution
- Blog: RE²: Region-Aware Relation Extraction from Visually Rich Documents
- Blog: LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-training
- Blog: VISA: Retrieval Augmented Generation with Visual Source Attribution
- Blog: Towards VQA Models That Can Read
- Blog: ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
- Blog: LEWIS: Latent Embeddings for Word Images and Their Semantics
- Blog: Text Change Detection in Multilingual Documents Using Image Comparison
- Blog: PatchFinder: Leveraging Visual Language Models for Accurate Information Retrieval Using Model Uncertainty
- Blog: Don’t Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
- Blog: TextLLM: a document multimodal large model based on dynamic resolution
- Blog: HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction
- Blog: Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
- Blog: DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation
- Blog: Form2Seq : A Framework for Higher-Order Form Structure Extraction
- Blog: Graph-Based Multimodal Contrastive Learning for Chart Question Answering
- Blog: One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction
- Blog: ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization
- Blog: SelfDoc: Self-Supervised Document Representation Learning
- Blog: HATFormer: Historic Handwritten Arabic Text Recognition with Transformers
- Blog: CloudScan - A configuration-free invoice analysis system using recurrent neural networks
- Blog: Towards Models that Can See and Read
- Blog: Partial Scene Text Retrieval
- Blog: Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps
- Blog: Smart Library: Identifying Books on Library Shelves Using Supervised Deep Learning for Scene Text Reading
- Blog: Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images
- Blog: MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
- Blog: Keyword Spotting from Online Chinese Handwritten Documents using One-versus-All Character Classification Model
- Blog: GMN: Generative Multi-modal Network for Practical Document Information Extraction
- Blog: MANGO: A Mask Attention Guided One-Stage Scene Text Spotter
- Blog: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
- Blog: LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
- Blog: Textual Visual Semantic Dataset for Text Spotting
- Blog: Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA
- Blog: ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
- Blog: BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
- Blog: SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering
- Blog: LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment
- Blog: What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
- Blog: VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding
- Blog: Enhanced Chart Understanding via Visual Language Pre-training on Plot Table Pairs
- Blog: LMDX: Language Model-based Document Information Extraction and Localization
- Blog: Visually Guided Generative Text-Layout Pre-training for Document Intelligence
- Blog: Extracting textual overlays from social media videos using neural networks
Showing 60 of 61 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_ocr_error_propagation_upstream_extractio_7e0eea9b,
title = {OCR error propagation (upstream extraction dependency)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/ocr-error-propagation-upstream-extraction-dependency/rdr_7e0eea9b81cd427a957e4eb4817b328e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_ocr_error_propagation_upstream_extractio_7e0eea9b_v1,
title = {OCR error propagation (upstream extraction dependency)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/ocr-error-propagation-upstream-extraction-dependency/rdr_7e0eea9b81cd427a957e4eb4817b328e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}