Document Image Understanding

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 92

All topics

OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents
Jul 10, 2026Yang Chen, Yunwen Li, Yufan Shen +6VLM Evaluation Document Understanding
Shanghai Artificial Intelligence Laboratory · Zhejiang University · M-A-P +2
LEGATO 2: Toward Multimodal Sheet Music Recognition and Understanding
Jul 7, 2026Guang Yang, Brian Siyuan Zheng, Victoria Ebert +1Optical Music Recognition Automatic Music Transcription
Paul G. Allen School of Computer Science & Engineering, University of Washington · Allen Institute for AI
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
Jul 6, 2026Gengluo Li, Xingyu Wan, Shangpin Peng +20Vision-Language Models Efficient VLM Inference
Institute of Information Engineering, Chinese Academy of Sciences · Large Language Model Department, Tencent · Nankai University
ClinOCR-Bench: A Comprehensive Clinical Scanned Document Dataset for Optical Character Recognition Model Evaluation
Jul 4, 2026Enshuo Hsu, Jin Zhou, Kirk RobertsVLM Evaluation Optical Character Recognition
McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA. · Enterprise Development & Integration, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
A Vision Based System for Guided and Collaborative Reconstruction of Fragmented Documents
Jul 3, 2026Oliver Krumpek, Diana LeoHuman-Robot Collaboration Cultural Heritage
Fraunhofer IPK, dept. Machine Vision, Pascalstr. 8-9, 10587 Berlin, Germany
SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence
Jul 2, 2026Saoud Aldowaish, Yashwanth Karumanchi, Kai-Chen Chiang +4Electronic Design Automation Document Image Understanding
The Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT, 48112 USA. · The Department of Electrical, Computer & Energy Engineering, University of Colorado Boulder, Boulder, CO 80309, USA.
DEMUN: Fast and accurate discovery of music notation in very large collections
Jun 30, 2026Vojtěch Dvořák, Filip Bím, Jiří Mayer +5Optical Music Recognition Visual Document Retrieval
Institute of Formal and Applied Linguistics, Charles University, Prague, Czechia · Moravian Library, Brno, Czechia
Multimodal Graph RAG for Long-range Visually Rich Document Understanding
Jun 27, 2026Yi-Cheng Wang, Chu-Song ChenMultimodal RAG Visual Question Answering
Department of Computer Science and Information Engineering, National Taiwan University · FinTech Center, National Taiwan University
Joint Transcription and Decryption of Images of Encrypted Handwritten Documents: A Comparison with the Traditional Pipeline
Jun 26, 2026Marino Oliveros-Blanco, Lei Kang, Alicia Fornés +1Optical Character Recognition Document Image Understanding
Computer Vision Center Department of Computer Science Universitat Aut`onoma de Barcelona, Spain · Department of Linguistics Stockholm University, Sweden
HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment
Jun 24, 2026Chuangxin Zhao, Boyan Shi, Yanling Wang +7VLM Evaluation Multimodal Grounding
An LMM for Precisely Grounding Elements in Documents
Jun 23, 2026Yijian Lu, Chuangxin Zhao, Kai Sun +3Visual Reasoning Large Vision-Language Models
Department of Computer Science and Technology, Tsinghua University · Institute of Automation, Chinese Academy of Sciences
RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild
Jun 22, 2026Cheng Cui, Tingquan Gao, Xueqing Wang +11Multi-Task Learning Document Layout Analysis
PaddlePaddle Team, Baidu Inc.
DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppression
Jun 21, 2026Sheng-Wei Chan, Jen-Shiun ChiangMamba Test-Time Adaptation
Department of Electrical and Computer Engineering, Tamkang University, New Taipei City, Taiwan
Text region detection in historical astronomical diagrams
Jun 14, 2026Zeynep Sonat Baltacı, Raphaël Baena, Fei Meng +4Document Understanding Historical Document Analysis
LIGM, ENPC, IP Paris, Univ Gustave Eiffel, CNRS, Marne-la-Vallée, France · LTE, CNRS, PSL-Observatoire de Paris, SU, EIDA Project
IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products
Jun 12, 2026Haonan Qi, Jin Cao, Yongqi Zhang +9Multimodal Large Language Models Multimodal Model Evaluation
Multimodal and Industrial AI TeamTaobao&Tmall, Alibaba Group
ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction
Jun 10, 2026LeKai Yu, Hao Liu, Kun Wang +4Document Parsing Document Layout Analysis
Shandong University · Southeast University
ERN-Net : Evolving Reason Node-Net for Document Binarization
Jun 10, 2026Hsin-Jui Pan, Sheng-Wei Chan, Jen-Shiung ChiangConvolutional Neural Networks Document Image Understanding
Dept. of Electrical Engineering Tamkang University
POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction
Jun 8, 2026Brandon Smock, Libin Liang, Max Sokolov +4Table Structure Recognition Multimodal Graph Learning
Kensho Technologies
MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models
Jun 8, 2026David Setiawan, Temuulen Khishigsuren, Milind Agarwal +3Low-Resource Language Processing Optical Character Recognition
λSchool of Computing and Information Systems, The University of Melbourne · ΨMelbourne School of Psychological Sciences, The University of Melbourne · ΦLILT
Intelligent Character Recognition of Handwritten Forms with Deep Neural Networks
Jun 7, 2026Hartwig GrabowskiOptical Character Recognition Document Image Understanding
Institute for Machine Learning and Analytics (IMLA) Offenburg University, Germany
DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization
Jun 7, 2026Sheng-Wei Chan, Yung-Che Wang, Hsin-Jui Pan +2Mamba Document Image Understanding
Department of Electrical and Computer Engineering, Tamkang University, No.151, Yingzhuan Rd., Tamsui Dist., New Taipei City, 251301, Taiwan
End-to-End Text Line Detection and Ordering
Jun 2, 2026Benjamin KiesslingDocument Layout Analysis Document Image Understanding
ALMAnaCH · ALMAnaCH, Inria, France
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Jun 2, 2026Zelun Zhang, Hongen Liu, Suyin Liang +12Data Selection Training Data Selection
PaddlePaddle Team, Baidu Inc.
Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis
Jun 1, 2026Catyana Heyne, Jürgen Frikel, Filippo RiccioDocument Understanding Multimodal Classification
OTH Regensburg, Germany
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
May 31, 2026Minglai Yang, Xinyan Velocity Yu, Pengyuan Li +22VLM Evaluation Document Parsing
2077AI · University of Arizona · University of Southern California +8
HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers
May 31, 2026Issa Sugiura, Shuhei Kurita, Yusuke Oda +1VLM Evaluation Data Visualization
Institute of Science Tokyo · NII LLMC · NII
ABot-OCR Technical Report
May 27, 2026Kaitao Jiang, Ruiyan Gong, Xiaolong Cheng +3Vision-Language Models Document Parsing
AMAP CV Lab Alibaba Group
Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing
May 25, 2026Kateryna Lutsai, Dana Křivánková, Pavel Straňák +1Document Understanding Historical Document Analysis
Institute of Formal and Applied Linguistics, Charles University MFF, Malostranské náměstí, Prague, 11800, Czech Republic. · Institute of Archaeology, Czech Academy of Sciences, Letenská, Prague, 11800, Czech Republic.
FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers
May 21, 2026Laziz Hamdi, Amine Tamasna, Pascal Boisson +1Table Structure Recognition Document Image Understanding
LITIS, Rouen Normandy, France · Malakoff Humanis, Paris, France
MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
May 21, 2026Bangbang Zhou, Hangdi Xing, Yifan Chen +8Document Parsing Document Layout Analysis
University of Science and Technology of China · Tongyi Lab, Alibaba Group

Jul 10, 2026, cs.CVJ/K move · Enter open · S save

OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents

Yang Chen, Yunwen Li, Yufan Shen, Minghao Liu+5

Shanghai Artificial Intelligence Laboratory · Zhejiang University · M-A-P+2

VLM Evaluation Document Understanding Visual Question Answering Visually Grounded Reasoning Document Image Understanding

Open paper AskPDF arXiv

Recent advancements in LVLMs necessitate robust benchmarks for complex, visually grounded reasoning. A critical limitation is identified in many document understanding benchmarks: visual content is often reducible to text, enabling high performance without genuine visual grounding. To address this limitation, OmniMapBench is introduced to foster visual-centric reasoning for map documents. The benchmark comprises 2,096 manually annotated question-answer pairs across 1,603 map documents from nine categories. It is designed to probe a hierarchy of skills, ranging from perception to multi-step visual reasoning. To quantify benchmark properties, a simple yet effective benchmark-level metric is proposed: the Visual Dependency Index (VDI), defined as the accuracy drop when images are replaced with question-agnostic descriptions. OmniMapBench exhibits higher VDI than established benchmarks, which quantitatively validates its focus on irreducible visual reasoning. Comprehensive evaluations of 25 leading LVLMs are conducted on OmniMapBench. A significant performance gap is observed, with the top-performing model achieving only 75.03% accuracy. This result underscores the challenges posed by OmniMapBench to current LVLMs. This work aims to catalyze progress in visual-centric reasoning for document understanding of LVLMs. The dataset and code are publicly available at https://github.com/SIGMME/OmniMapBench.

Momentum

Related topics

Latest papers 92