PPaperPicks
← All conferences
Editions20262025

ICDAR 2026

A

International Conference on Document Analysis and Recognition

Official site ↗
89
accepted papers
337
authors
August 30 - September 4, 2026
dates
Austria
location

89 / 89 papers

  1. 1
    A MambaVision-Based Cross-Modal Feature Enhancement Network for Scene Text Super-Resolution
    Ruichang Zhu
    ,
    Hongxi Wei
    ,
    Bo Sun
    ,
    Heng Wang
  2. 2
    A Millennium of Arabic Manuscripts in Three Styles: A Line-Level OCR Benchmark for Naskh, Taliq, and Nastaliq
    Maxim Novopoltsev
    ,
    Ruslan Murtazin
    ,
    Andrey Sakhovskiy
    ,
    Emilia Bojarskaja
    ,
    Vladimir Kokh
    ,
    Ivan Ulitin
    ,
    Botirjon Abdullayev
    ,
    Khamidulla Aminov
    ,
    Masudkhon Ismoilov
    ,
    Semen A. Budennyy
  3. 3
    Active Reference Acquisition in Few-Shot Font Generation
    Shinnosuke Matsuo
  4. 4
    Adaptive Hybrid Machine Translation for E-commerce: A Reinforcement Learning Approach to Arabic Localization
    Ayman Hanafy
    ,
    Farhan Khawar
  5. 5
    Ambiguity-Controlled Handwritten Mathematical Expression Generation via Harmonized Dual-Conditional Guidance
    Ryo Ishiyama
    ,
    Takaya Kawakatsu
  6. 6
    An Analysis of Lightweight Models for Document Image Machine Translation
    Abantika Bose
    ,
    Thomas Gorges
    ,
    Lukas Hüttner
    ,
    Linda-Sophie Schneider
    ,
    Mathias Seuret
    ,
    Fei Wu
    ,
    Vincent Christlein
  7. 7
    An Exploratory Study of Text-to-Image Generation for Query-by-Example Retrieval of Historical Document Images
    Melissa Cote
    ,
    Alexandra Branzan Albu
  8. 8
    Angkorian-KSI: A Multi-task Benchmark for Khmer Stone Inscription Analysis
    Nimol Thuon
    ,
    Jun Du
    ,
    Ranysakol Thuon
    ,
    Panhapin Theang
  9. 9
    Automated Character-Level Annotation for Historical Nom Documents via an Iterative Self-updating Radical-Based Recognizer
    Cuong Tuan Nguyen
    ,
    Khoa Nguyen Tran
    ,
    Ngoc Tuan Nguyen
    ,
    Hung Tuan Nguyen
    ,
    Nam Tuan Ly
    ,
    Masaki Nakagawa
  10. 10
    Automatic Layout Detection in Historical Civil Records Using Deep Object Detection
    Wissam AlKendi
    ,
    Franck Gechter
    ,
    Laurent Heyberger
    ,
    Christophe Guyeux
  11. 11
    Benchmarking Information Retrieval for Large Archives of Historical Documents
    Tobias Steiner
    ,
    Merlin Streilein
    ,
    Andreas Fischer
    ,
    Kaspar Riesen
  12. 12
    BinDiffuser: Learning Binarization Style Priors to Guide Diffusion Models for Palm-Leaf Document Binarization
    K. H. Salman
    ,
    Chakravarthy Bhagvati
  13. 13
    Bridging the Gaps: Learning to Estimate Missing Text in Fragmentary Greek Inscriptions
    Silvia Zottin
    ,
    Axel De Nardin
    ,
    Maddalena Zunino
    ,
    Valentina Mignosa
    ,
    Gian Luca Foresti
  14. 14
    BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval
    Marco Peer
    ,
    Anna Scius-Bertrand
    ,
    Patricia Scheurer
    ,
    Andreas Fischer
  15. 15
    Can VLMs Understand Handwritten Mathematical Documents?
    Shree Mitra
    ,
    Ajoy Mondal
    ,
    C. V. Jawahar
  16. 16
    Conversational Retrieval and On-the-Fly Knowledge Modeling of Historical Penitentiary Repression Records
    Paula Font Solà
    ,
    Adrià Molina Rodríguez
    ,
    Josep Lladós Canet
  17. 17
    CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents
    Martin Kostelník
    ,
    Michal Hradis
    ,
    Martin Docekal
  18. 18
    DDD - A Diagnostic Dataset for Character Recognition and Detection on Ancient Egyptian Hieratic Characters and Words
    Stephan M. Unter
    ,
    Elena L. Hertel
  19. 19
    DeChart: A Benchmark and Text-Enhanced Chart-to-Table Conversion Method with Multimodal LLMs
    Chen-Yu Xie
    ,
    Xiao-Hui Li
    ,
    Fei Yin
    ,
    Cheng-Lin Liu
  20. 20
    DiffusionRec: Recognition-Guided Diffusion for Content-Aware Urdu Handwriting Generation
    Saima Kausar
    ,
    Ayesha Amjad
    ,
    Ahmad Sarmad Ali
    ,
    Momina Moetesum
    ,
    Adnan Ul-Hasan
    ,
    Faisal Shafait
  21. 21
    Doc2Doc: Structure-Aware Generative Rendering for Bi-directional Document Translation
    Fahad Al-Otaibi
    ,
    Daulet Toibazar
    ,
    Renad A. Alnuaim
    ,
    Ranya A. Alkahtani
    ,
    Haneen A. Alhomoud
    ,
    Asma A. Ibrahim
    ,
    Yazeed Alharbi
    ,
    Murtadha Al-Jubran
    ,
    Pedro J. Moreno
  22. 22
    DocCenter: Center and Corner Aware Representation for Robust Multi-document Localization
    Mengyuan Zhao
    ,
    Kun Xu
    ,
    Xin Cheng
    ,
    Ting Li
    ,
    Qiuman Tan
    ,
    Xinyao Zhang
  23. 23
    Document Analysis and Recognition - ICDAR 2025 - 19th International Conference, Wuhan, China, September 16-21, 2025, Proceedings, Part I
    Xu-Cheng Yin
    ,
    Dimosthenis Karatzas
    ,
    Daniel Lopresti
  24. 24
    Document Analysis and Recognition - ICDAR 2025 - 19th International Conference, Wuhan, China, September 16-21, 2025, Proceedings, Part II
    Xu-Cheng Yin
    ,
    Dimosthenis Karatzas
    ,
    Daniel Lopresti
  25. 25
    Document Analysis and Recognition - ICDAR 2025 - 19th International Conference, Wuhan, China, September 16-21, 2025, Proceedings, Part III
    Xu-Cheng Yin
    ,
    Dimosthenis Karatzas
    ,
    Daniel Lopresti
  26. 26
    Document Analysis and Recognition - ICDAR 2025 - 19th International Conference, Wuhan, China, September 16-21, 2025, Proceedings, Part IV
    Xu-Cheng Yin
    ,
    Dimosthenis Karatzas
    ,
    Daniel Lopresti
  27. 27
    Document Analysis and Recognition - ICDAR 2025 - 19th International Conference, Wuhan, China, September 16-21, 2025, Proceedings, Part V
    Xu-Cheng Yin
    ,
    Dimosthenis Karatzas
    ,
    Daniel Lopresti
  28. 28
    Document Analysis and Recognition - ICDAR 2025 Workshops - Wuhan, China, September 20-21, 2025, Proceedings, Part I
    Lianwen Jin
    ,
    Richard Zanibbi
    ,
    Veronique Eglin
  29. 29
    Document Analysis and Recognition - ICDAR 2025 Workshops - Wuhan, China, September 20-21, 2025, Proceedings, Part II
    Lianwen Jin
    ,
    Richard Zanibbi
    ,
    Veronique Eglin
  30. 30
    Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
    Amritansh Maurya
    ,
    Navjot Singh
    ,
    Mohammed Javed
    ,
    Omar Moured
  31. 31
    EMBLEM: Enhancing Multi-script Table Detection through Masking
    Dhruv Kudale
    ,
    Udhay Brahmi
    ,
    Ganesh Ramakrishnan
  32. 32
    Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead
    Jindong Li
    ,
    Dario Zanca
    ,
    Vincent Christlein
    ,
    Tim Hamann
    ,
    Jens Barth
    ,
    Peter Kämpf
    ,
    Björn M. Eskofier
  33. 33
    EpiSAM: Character Segmentation in Challenging Stone Inscriptions
    Arnav Sharma
    ,
    Pratyush Jena
    ,
    Amal Joseph
    ,
    Ravi Kiran Sarvadevabhatla
  34. 34
    Evaluating Feedback by Iterative Repair of Multi-step Solution Documents
    Tobias Lengfeld
    ,
    Jakob Seitz
    ,
    Radu Timofte
  35. 35
    Evaluating Vision-Language Models on Historical Postcards
    Matthieu Pelingre
    ,
    Salvatore Tabbone
  36. 36
    Few-Shot Writer Adaptation via Multimodal In-Context Learning
    Tom Simon
    ,
    Pierrick Tranouez
    ,
    Stéphane Nicolas
    ,
    Clément Chatelain
    ,
    Thierry Paquet
  37. 37
    Figures as Evidence: Multi-image Scientific Generation
    Jawad Ibn Ahad
    ,
    Mritunjoy Chakraborty
    ,
    Fuad Rahman
    ,
    Sifat Momen
    ,
    Shafin Rahman
    ,
    Nabeel Mohammed
  38. 38
    From Chunks to Graphs: Training-Free Multimodal Late Interaction for Document Understanding
    Ayush Lodh
    ,
    Souparni Mazumder
    ,
    Sanket Biswas
    ,
    Josep Lladós
    ,
    Nisha Singh Chauhan
  39. 39
    From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction
    Uddipan Basu Bir
    ,
    Vincent Christlein
    ,
    Andreas K. Maier
    ,
    Mathias Zinnen
  40. 40
    G2I: A Progressive Structure-to-Detail Curriculum Training Strategy for Handwritten Mathematical Expression Recognition
    Minzhi Zhang
    ,
    Xingxiang Zhou
    ,
    Ziming Li
    ,
    Jie Zhang
    ,
    Zhi Chen
    ,
    Xiangdong Su
  41. 41
    Generalized Open-set Single-shot Character Recognition on Ancient Egyptian Hieratic Characters
    Stephan M. Unter
    ,
    Chang Liu
    ,
    Elisa H. Barney Smith
  42. 42
    GLiDRE: Generalist Lightweight Model for Document-Level Relation Extraction
    Robin Armingaud
    ,
    Romaric Besançon
  43. 43
    GRACE: Gradient-Regulated Approach for Consistent Explanations
    Sayantan Basu
  44. 44
    GraphVLM: Combining VLMs with GraphMLLM for Document Understanding
    Shuai Li
    ,
    Xiao-Hui Li
    ,
    Hai-Jie Yuan
    ,
    Fei Yin
    ,
    Lin-Lin Huang
  45. 45
    GSMP: Geometry-Structured Masked Pre-training with Multi-granularity Objectives and Curriculum Learning for Geometric Problem Solving
    Ziming Li
    ,
    Jie Zhang
    ,
    Xingxiang Zhou
    ,
    Minzhi Zhang
    ,
    Zhi Chen
    ,
    Guanglai Gao
    ,
    Xiangdong Su
  46. 46
    HIDRA: Hierarchical Ink-Aware Dual-Granularity Retrieval Architecture for Historical Fragments
    Jihad Al Akl
    ,
    Chady Abou Jaoude
    ,
    Zahi Al Chami
    ,
    Marianne Abi Kanaan
    ,
    Abdallah Makhoul
  47. 47
    Hierarchical Co-embedding of Font Shapes and Impression Tags
    Yugo Kubota
    ,
    Kaito Shiku
    ,
    Seiichi Uchida
  48. 48
    Hierarchical Stroke-Level Clustering and Step-Level Segmentation for Automatic Scoring of Geometric Construction Answers with an Electronic Drawing Compass
    Thanh-Nghia Truong
    ,
    Hung Tuan Nguyen
    ,
    Nam Tuan Ly
    ,
    Yoichi Tsuchida
    ,
    Hiroshi Miyazawa
    ,
    Tomo Asakura
    ,
    Masamitsu Ito
    ,
    Toshihiko Horie
    ,
    Fumiko Yasuno
    ,
    Masaki Nakagawa
  49. 49
    HME-Leibniz: A Multi-level Mathematical Expression Dataset from Leibniz's Manuscripts
    Yejing Xie
    ,
    Ze Qian
    ,
    Yunfan Li
    ,
    Harold Mouchère
    ,
    David Rabouin
  50. 50
    Identify, Locate, Link: End-to-End Key-Value Extraction from Document Images
    A. Said Gurbuz
    ,
    Ahmed S. Nassar
    ,
    Christoph Auer
    ,
    Maksym Lysak
    ,
    Lucas Morin
    ,
    Matteo Omenetti
    ,
    Tim Strohmeyer
    ,
    Panagiotis Vagenas
    ,
    Nikolaos Livathinos
    ,
    Michele Dolfi
    ,
    Peter W. J. Staar