IAPR TC11 Newsletter 2025 02
February, 2025
Click on the buttons below to view sections of the newsletter.
- Message from the Editor
- Dates and Deadlines
- Deadlines
- Upcoming Conferences and Events
- Open Call for Organizing DAR Events *(repost)*
- ACPR 2025 - Call for Papers for the 8th Asian Conference on Pattern Recognition
- ICDAR 2025 - Call for Papers *(repost)*
- DAR-Related Competitions
- ICDAR 2025 Competition on Comics Understanding in the Era of Foundational Models
- Inference Attacks Against Document VQA (Red Teaming Competition at SaTML 2025) *(updated)*
- ICDAR 2025 Competition on Automatic Classification of Literary Epochs (CoLiE) *(repost)*
- ICDAR 2025 Competition on Historical Map Text Detection, Recognition and Linking *(repost)*
- Datasets
- TC11 Datasets Repository
- Where to share datasets
- TC11 Datasets Repository
Dear TC11 members,
In this issue, find our open call for organizing the major DAR events that will be held in the coming years, the calls for papers for ICDAR 2025 and ACPR 2025.
There is also a number of calls for participation in competitions with new and interesting research problems in the DAR field.
Happy reading!
Nibal Nayef, TC11 Communication Officer
( n.nayef@gmail.com )
Join us! If you are not already a member of the TC11 community, please consider joining the TC11 mailing list. Follow us on X (Twitter) (iapr_tc11): https://twitter.com/iapr_tc11
Deadlines
2025
- Feb 28 ICDAR paper title & abstract submission (today)
- March 07 ICDAR full paper submission (firm deadline)
- June 03 ACPR abstract submission
- June 10 ACPR full paper submission
Upcoming Conferences and Events
2025
- IGS 2025. Polytechnique Montréal, Canada (June 2-5, 2025)
- ICDAR 2025. Wuhan, Hubei, China (September 16-21, 2025)
- ACPR 2025. Gold Coast, Australia (November 10-13, 2025)
The IAPR technical committees on graphics recognition (TC10) and reading systems (TC11) are regularly organizing scientific events for the Document Analysis and Recognition (DAR) community, including the ICDAR flagship conference.
In addition to specific calls for bids to host one of the events, we encourage teams to announce their interest in organizing one of the following events:
- ICDAR: International Conference on Document Analysis and Recognition (annually; next possibility in 2028)
- DAS: International Workshop on Document Analysis Systems (satellite event of ICDAR in even years; next possibility in 2026)
- HIP: International Workshop on Historical Document Imaging and Processing (satellite event of ICDAR in odd years; next possibility in 2025)
- GREC: International Workshop on Graphics Recognition (satellite event of ICDAR in odd years; next possibility in 2025)
- SSDA: Summer School on Document Analysis (biannually in odd years; next possibility in 2025)
You may find the details of each specific call in the previous or future issues of this newsletter or in the respective websites of each event.
Anyone interested in hosting one of these events is invited to announce their interest via email to jean-christophe.burie@univ-lr.fr and andreas.fischer@unifr.ch, in order to receive feedback and support for preparing a proposal.
Jean-Christophe Burie (Chair, TC10)
Andreas Fischer (Chair, TC11)
The 8th Asian Conference on Pattern Recognition (ACPR 2025) will be hosted from November 10 to 13, 2025 on the Gold Coast of Australia.
Conference Dates
- November 10, 2025: Workshops and Tutorials
- November 11-13, 2025: Main Conference
Important Dates
- Abstract Submission: June 3, 2025
- Full Paper Submission: June 10, 2025
- Notification to Authors: August 10, 2025
- Camera-ready Submission: August 31, 2025
ACPR 2025 solicits high-quality original research for publication. This conference provides an excellent opportunity to nurture new ideas and collaborations for students, academics, and industry researchers. Topics of interest include pattern recognition, computer vision, signal processing and DAR-related topics such as handwriting recognition, document analysis and understanding and multimedia analysis and retrieval (under the topic of “media processing and interaction”). The full call for papers can be found here.
You may find other information from the website of the conference (https://acpr2025.com/).
ICDAR is the premier event for scientists and practitioners involved with document analysis and recognition, a field of growing importance in our current age of digital transition. The 19th edition of this flagship conference will be held in Wuhan, September 16-21, 2025.
Conference Paper Submissions:
The submission details for the standard conference paper track at ICDAR 2025 can be found at:
https://www.icdar2025.com/submission/call-for-papers
Now, the submission site is open at:
https://cmt3.research.microsoft.com/ICDAR2025
The Review of conference papers will be double blind. Authors should not include their names, affiliations, or acknowledgements in submitted manuscripts, and should ensure that their identity is not revealed indirectly by citing their earlier work in the third person.
Papers may be up to 15 pages long (not including references) in Springer Lecture Notes in Computer Science (LNCS) format. Detailed submission instructions for authors can be found on the conference website: (https://www.icdar2025.com/).
Important Dates (firm deadlines, no further extension)
- Feb 28, 2025: Conference Title & Abstract submission deadline
- March 7, 2025: Conference full paper upload and editing closed
- May 24, 2025: Conference paper acceptance notification
- June 20, 2025: Camera-Ready due
Publication: Springer Lecture Notes in Computer Science
The conference proceedings will be published as part of the Springer Lecture Notes in Computer Science (LNCS) series. Accepted papers will be freely available through SpringerLink from the conference website for one year after publication, and will later be freely available through SpringerLink four years after publication.
Contact:
Xu-Cheng Yin xuchengyin@ustb.edu.cn
Dimosthenis Karatzas dimos@cvc.uab.es
Daniel Lopresti lopresti@cse.lehigh.edu
ICDAR 2025 Competition on Comics Understanding in the Era of Foundational Models
With the recent advancements in Comics’ single-page understanding, we are pleased to announce the ICDAR Competition on “Comics Understanding in the Era of Foundational Models”. This challenge aims towards a deeper understanding of Comics Panel sequences, and introduces five subtasks formulated as “Pick-A-Panel”, where the goal is to pick the correct panel among options. The subtasks are:
- Sequence filling: in a sequence of 5 comic panels, one panel has been removed. Pick from the provided options, the correct missing panel.
- Character-closure: in a sequence of 5 sorted panels, the last panel has been removed. The two provided options are the same panel, but the text in the speech bubbles has been swapped, pick the correct one.
- Visual-closure: in a sequence of 5 sorted panels, the last panel has been removed. The text has been removed from the provided panel options, can you pick the correct one without the text?
- Text-closure: in a sequence of 5 sorted panels, the last panel has been removed. The provided options are all the same panel, but the text in the speech bubbles has been changed, pick the panel with the correct text.
- Caption relevance: a caption of a comic panel is provided and a set of option panels, pick the panel that follows after the caption.
The competition is hosted at the Robust Reading Competition platform: https://rrc.cvc.uab.es/?ch=31
Download the dataset in Huggingface: https://huggingface.co/datasets/VLR-CVC/ComicsPAP
Important dates:
- February 19th: Test/Val sets available
- February 25th: Benchmark model and Dev set available
- April 15th: Deadline for Competition submissions
- April 20th: Initial submission of competition report
- April 30th: Camera-ready of competition report
- September 16-21: ICDAR 2025 Conference
Organizers:
- Emanuele Vivoli (Computer Vision Center, and MICC University of Florence)
- Artemis Llabrés (Computer Vision Center)
- Mohamed Ali Soubgui (Computer Vision Center)
- Dimosthenis Karatzas (Computer Vision Center)
Contact: comics@cvc.uab.cat
Looking forward to benchmarking your comics panel sequence models!
Inference Attacks Against Document VQA (Red Teaming Competition at SaTML 2025) (updated)
We are excited to invite you and your colleagues to participate in the Red Teaming Competition at SaTML 2025, titled “Inference Attacks Against Document VQA”, which focuses on privacy vulnerabilities in Document Visual Question Answering (DocVQA) models. This competition presents a unique opportunity to explore critical privacy concerns in AI, specifically through the development of membership inference and reconstruction attacks tailored to DocVQA models.
More details, including competition rules and registration, can be found on the official website: https://benchmarks.elsa-ai.eu/?ch=2&com=introduction.
Important Dates:
- Submission Deadline: March 07, 2025
- Announcement of Winning Teams: March 17, 2025
- Competition Track: April 9-11, 2025 (during SaTML 2025)
For any inquiries or further information, please do not hesitate to contact us at: info_pfl@cvc.uab.cat.
We look forward to your participation and the innovative solutions you will bring to this critical area of AI privacy research.
The competition is organized by the European Lighthouse on Secure and Safe AI (ELSA).
Organizers:
Andrey Barsky (Computer Vision Center)
Antti Honkela (University of Finland)
Aurélie Joseph (YOOZ)
Dimosthenis Karatzas (Computer Vision Center)
Raouf Kerkouche (CISPA)
Ernest Valveny (Computer Vision Center)
Joonas Jälkö (University of Finland)
Kangsoo Jung (INRIA)
Khanh Nguyen (Computer Vision Center)
Marlon Tobaben (University of Finland)
Mario Fritz (CISPA)
Mohamed Ali Souibgui (Computer Vision Center)
Vincent Poulain d’Andecy (YOOZ)
ICDAR 2025 Competition on Automatic Classification of Literary Epochs (CoLiE) (repost)
We are pleased to announce the ICDAR 2025 Competition on Automatic Classification of Literary Epochs (CoLiE), which aims to push the boundaries of temporal text analysis by challenging participants to develop state-of-the-art methods for dating literary texts. The competition focuses on leveraging natural language processing (NLP) and information retrieval (IR) techniques to predict the time periods in which texts were written.
Overview
The CoLiE competition offers two main tasks to address temporal classification and the understanding of historical texts:
Task 1: Literary Epochs Classification
This task focuses on classifying texts based on literary epochs and their subdivisions:
Sub-task 1.1:
Classification of texts into six major literary epochs when the corresponding books were written: (1) Classicism (1660-1798), (2) Romanticism (1798-1837), (3) Victorian Literature (1837-1901), (4) Modernism (1900-1945), (5) Postmodernism (1945-2000), and (6) Contemporary (from 2000).
Sub-task 1.2:
Classification of texts into particular epoch subdivisions: early (first quarter of the epoch), middle (middle half), and late (final quarter). These periods differ in length between epochs (due to the different lengths of the corresponding epochs). Also, the epochs of Classicism, Romanticism, Victorian Literature, Modernism, and Postmodernism epochs were divided into three periods, while the Contemporary epoch is divided into only two periods.
Task 2: ChronoText Classification
This task addresses temporal granularity by focusing on:
Sub-task 2.1: Identifying the century of origin for a given text.
Sub-task 2.2: Pinpointing the specific decade within that century when the text was composed.
Participation
We invite researchers, practitioners, and enthusiasts from IR and NLP communities to participate in this exciting competition.
How to Participate:
- Visit our website: https://colie.pro/
- Familiarize yourself with the tasks, competition rules, datasets, and evaluation metrics
- Submit your results through the Kaggle competition platform
Important Dates
- December 17, 2024: The competition website is live and open to participants. Training and validation sets, together with their labels, are available
- April 1, 2025: Test dataset available
- April 8, 2025: Deadline for competition participants
- May 1, 2025: Submission of competition reports
- May 16, 2025: Camera-ready paper
- June 30, 2025: Communicate winners to chairs
- September 16-21, 2025: Presentation of results at the special session at the ICDAR conference
Contact
For any inquiries, please contact the competition organizers at: colie2025.competition@gmail.com.
We look forward to your participation and innovative contributions to the field of temporal text analysis!
Organizers
Marina Litvak, SCE (marinal@ac.sce.ac.il)
Irina Rabaev, SCE (irinar@ac.sce.ac.il)
Ricardo Campos, University of Beira Interior, INESC TEC (ricardo.campos@ubi.pt)
Alípio Jorge, University of Porto, INESC TEC (amjorge@fc.up.pt)
Adam Jatowt, University of Innsbruck (adam.jatowt@uibk.ac.at)
Roza Bass, SCE (rozzaba@ac.sce.ac.il)
Hugo Sousa, University of Porto, INESC TEC (hugo.sousa@fc.up.pt)
ICDAR 2025 Competition on Historical Map Text Detection, Recognition and Linking (repost)
Overview
The 2025 ICDAR competition focuses on detecting, recognizing, and linking text in historical map images. New features of this competition edition include expanded French Land Registers and Taiwanese map datasets, synthetic training data, and enhanced evaluation metrics.
Registration and details: https://rrc.cvc.uab.es/?ch=32.
The training and validation sets are already available.
Join our Google Group to receive updates: https://groups.google.com/g/icdar25-maptext-news
Submission deadline: April 1, 2025.
Call for participants
After a successful 2024 edition, we are pleased to announce the 2025 edition of the ICDAR Competition on Map Text Detection, Recognition, and Linking. This edition still focuses on text detection and recognition in challenging historical map images, and introduces several new features:
- expanded data for the French Land Registers dataset
- addition of a new Taiwanese maps dataset from the GIS Center at Academia Sinica, featuring Chinese characters
- release of large synthetic training data for each dataset
- improved evaluation metrics and indicators for better feedback
We would like to invite you to register and participate using the following links:
- Official competition platform: https://rrc.cvc.uab.es/?ch=32
- Receive updates by email: https://groups.google.com/g/icdar25-maptext-news
Important dates
- December 10, 2024: Website live, train/val sets available
- March 1, 2025: Test set available, submissions are open
- April 1, 2025: Final submission deadline, including short reports
Task Overview
The competition encompasses four tasks:
1. word detection
2. phrase detection
3. word detection and recognition
4. phrase detection and recognition.
Detailed descriptions for each task can be found on the official web page: https://rrc.cvc.uab.es/?ch=32&com=tasks
Contact: icdar25-maptext-contact (at) googlegroups.com
This competition is organized by experienced competition organizers from the following organizations:
University of Minnesota (USA), Grinnell College (USA), Univ Gustave Eiffel, ENSG, IGN, LASTIG (France), EHESS (France), EPITA (France), Academia Sinica (Taiwan).
Looking forward to benchmarking your innovative solutions!
— ICDAR 2025 MapText Organizers
TC11 Datasets Repository
Did you know it? We have two official places for datasets:
- Our historical platform for storage and listing: http://datasets.iapr-tc11.org
- A Zenodo community (if you choose to submit your datasets there): https://zenodo.org/communities/iapr-tc11
TC11 maintains a collection of datasets that can be found online in the TC11 Datasets Repository.
If you have new datasets (e.g., from competitions) that you wish to share with the research community, please use the online upload form. For questions and support, please contact the TC11 Dataset Curator (contact information is below).
Joseph Chazalon (TC11 Dataset Curator)
( joseph.chazalon@epita.fr )
Call for Contributions: To contribute news items, please send a short
email to the editor, [Nibal Nayef](mailto:n.nayef@gmail.com).
Contributions might include conference and workshop
announcements/updates/reports, career opportunities, book reviews, or anything
else of interest to the TC-11 community.
Subscription: This newsletter is sent to subscribers of the IAPR TC11 mailing list. To join the TC-11 mailing list, please click on this link: Join the TC-11 Mailing List. To manage your subscription, please visit the mailing list homepage: TC-11 Mailing List Homepage.