Document Image Understanding

Overview

Document image understanding studies how to interpret scanned, photographed, and digital pages, from recognizing text to recovering layout, tables, diagrams, and meaning across pages. Common approaches include OCR paired with layout detection and reading-order models, specialized table or handwriting recognizers, and end-to-end vision-language models; retrieval-augmented systems use these outputs to answer questions with document evidence. Benchmarks test tasks such as text extraction, document question answering, table parsing, and multilingual or multi-page understanding. Models have improved on clean pages, but real-world degradation, rare scripts, complex layouts, and long-range evidence integration remain difficult, and strong text accuracy does not always translate into reliable downstream answers.

Latest papers

CardsList

150 papers6 papers in the last four weeks, down 45% on the four weeks before. 0.0% of all new papers.

  1. RE-SciVQA: Improving Scientific VQA With Context-Relevant Retrieval and Lightweight MLLM Adaptation

    Oct 30, 2026Sheikh Tahmim Mehdi, Muminul Islam JamiVisual Question AnsweringScientific QA

  2. Frugal Handwritten Text Recognition for Sub-Saharan Civil-Status Registers: A Smartphone-to-Records Pipeline with CPU-Only Inference

    Oct 27, 2026Ousmane Hamadou, Jean Louis Kedieng Ebongue FendjiOptical Character RecognitionDocument Image Understanding

  3. Data Quality in RVL-CDIP: A Systematic Audit

    Oct 23, 2026Stefan Larson, Kevin LeachDocument Image UnderstandingData Leakage

  4. OCRia-1 Technical Report

    Oct 22, 2026Aman Rangapur, Antonio Jimeno Yepes, Daniel Bustamante +4Document ParsingDocument Image Understanding

  5. Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis

    Oct 20, 2026Mohammad Kawsar, Al Amin Islam Ridoy, Md Rakib Hossain +4Electronic Design AutomationDocument Image Understanding

  6. OvisOCR3 Technical Report

    Oct 20, 2026Yu Xia, Yinglun Li, Yuhui Chen +12Optical Character RecognitionDocument Image Understanding

  7. Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation

    Oct 14, 2026Yuheng Chen, Yufan Chen, Zhuojun Cai +8Document Parsing BenchmarksDocument Parsing

  8. LED-BENCH: A Benchmark for Large-format Engineering Drawing Understanding

    Oct 14, 2026Ke Li, Tianyi Wang, Enning You +4Document UnderstandingDocument Image Understanding

  9. ProtoSemImage: Image-Valued Prototypes with Deformable Row Alignment for Interpretable Document Classification

    Oct 8, 2026Mohammad Zare, Pirooz ShamsinejadbabakiText ClassificationPrototype-Based Classification

  10. PlotGround: Grounding Plot Digitization in Real Scientific Figures and Their Source Data

    Oct 5, 2026Yaohui Zhang, Binxu Li, Haoyi Duan +7Scientific VisualizationChart QA

  11. Color Independent Word Segmentation From Transcribed Bangla Passages

    Oct 1, 2026Faias Satter, Noor Masrur, Sk. Md. Masudul AhsanOptical Character RecognitionDocument Image Understanding

  12. Unapologetically Distributed: A Call for Decentralized Document Analysis

    Sep 30, 2026Adrià Molina, Oriol Ramos Terrades, Josep LladósOOD GeneralizationDecentralized Learning

  13. Xiaomi-OCR-0 Technical Report

    Sep 28, 2026Xin Chen, Anan Du, Feng Feng +7Vision-Language ModelsDocument Parsing

  14. The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models

    Sep 25, 2026Christoph Walser, Mauricio Fadel Argerich, Jonathan FürstDocument Information ExtractionEnergy-Efficient ML

  15. DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents

    Sep 21, 2026Jeremy Cerwin Wang, Wai Kit Wong, Jeff Kai Tai TangDocument Information ExtractionDocument Image Understanding

  16. Mind the Gaps: A Curated Benchmark for Form Field Detection

    Sep 20, 2026Iheb Brini, Omar Moured, Hamza Gbada +1Document Layout AnalysisDocument Image Understanding

  17. EMBLEM: Enhancing Multi-script Table Detection through Masking

    Sep 8, 2026Dhruv Kudale, Udhay Brahmi, Ganesh RamakrishnanTable Structure RecognitionDocument Image Understanding

  18. When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

    Sep 7, 2026Quentin Telnoff, Emanuela Boros, Mickaël Coustaty +3Explainable Artificial IntelligenceExplainable Image Classification

  19. KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records

    Sep 3, 2026Tasmiad Hasan, Arafat Zaman Ratul, Sarker Sadman Saalim +3Legal Document AnalysisLegal QA

  20. Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

    Sep 2, 2026Alejandro Barón García, Feng Wang, Emilia Garcia Casademont +1Efficient VLM InferenceSpeculative Decoding

  21. Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning

    Aug 31, 2026Yue Zhou, Yuan Wu, Yi ChangVLM EvaluationLarge Vision-Language Models

  22. OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding

    Aug 31, 2026Gengxu Li, Yuan Wu, Yi ChangVisual ReasoningMultimodal Reasoning

  23. Lot Machine: Multimodal Lot Extraction from Auction Catalogs

    Aug 31, 2026Mathias Zinnen, Alisha Mund, Sabine Lang +3VLM EvaluationDocument Image Understanding

  24. Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models

    Aug 29, 2026Jinghao Liu, Xingrun Liu, Gengchen Sun +3Document Image UnderstandingDocument Layout Analysis