IAPR TC11 Newsletter 2022 09

From TC11
Revision as of 10:26, 30 September 2022 by Afischer (talk | contribs) (Created page with "<center> 100px 140px </center> == September, 2022 == <hr> <br> Click on the buttons below to view sections of th...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
IAPR logo.gif Tc-11 Logo v2 72dpi.png

September, 2022



Click on the buttons below to view sections of the newsletter.

  • Message from the Editor
  • Dates and Deadlines
    • Deadlines
    • Upcoming Conferences and Events
  • ICDAR 2023
    • ICDAR 2023: Call for Papers
    • ICDAR 2023: Call for ICDAR-IJDAR Journal Track Papers
    • ICDAR 2023: Call for Competitions
  • Careers
    • Tenure-Track Assistant Professor Position (Computer Vision)
    • Postdoctoral Research Position on Document Intelligence and Privacy Preserving Learning
  • Datasets
    • TC11 Datasets Repository *(repost)*



Dear TC11 members,

The organizers of the 17th International Conference on Document Analysis and Recognition (ICDAR 2023) have issued several calls that are provided in this newsletter, including a call for competition proposals (deadline October 28, 2022), a call for ICDAR-IJDAR journal track papers (deadline October 31, 2022), and a call for conference papers (deadline January 15, 2023).

In the careers section, you will find a tenure-track Assistant Professor position in computer vision (RIT, Rochester, NY) and a Postdoc position on document intelligence and privacy preserving learning (CVC, Barcelona).

Andreas Fischer, TC11 Communications Officer
( andreas.fischer@hefr.ch )

Join us! If you are not already a member of the TC11 community, please consider joining the TC11 mailing list. Follow us on Twitter (iapr_tc11): https://twitter.com/iapr_tc11



Deadlines

2022

  • October 28 Competition Proposal Due ICDAR 2023
  • October 31 1st round journal track submission ICDAR 2023

2023

Upcoming Conferences and Events

2022

2023 and Later

  • ICDAR 2023. San José, USA (August 21-26, 2023)
  • ICDAR 2024. Athens, Greece (September, 2024)



ICDAR 2023: Call for Papers

The 17th International Conference on Document Analysis and Recognition (ICDAR 2023)
August 21-26, 2023 San José, California, USA
https://icdar2023.org/
PDF version of this call: ICDAR 2023 CfP

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 17th edition of this flagship conference will be held in San Jose, August 21-26, 2023. (The conference will be an in-person event).

Important Dates

Jan 15, 2023  Conference paper submission (23:59 AoE)
Mar 26, 2023  Conference paper notification
Apr 15, 2023  Conference camera-ready papers due

Paper Submissions:

There is both a standard conference paper track and a journal track at ICDAR 2023; details regarding the journal track may be found in a separate Call for Papers on the conference website.

Reviewing for 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 (including references) in Springer Lecture Notes in Computer Science (LNCS) format. Detailed submission instructions for authors can be found on the conference website (https://icdar2023.org).

Topics of Interest:

  • Document image processing
  • Physical and logical layout analysis
  • Text and symbol recognition
  • Handwriting recognition
  • Document analysis systems
  • Document classification
  • Indexing and retrieval of documents
  • Document synthesis
  • Extracting document semantics
  • NLP for document understanding
  • Office automation
  • Graphics recognition
  • Human document interaction
  • Document Representation Modeling
  • Structured document generation
  • Multimedia document analysis
  • Mobile text recognition
  • Pen-based document analysis
  • Scene text detection and recognition
  • Recognition of tables and formulas
  • Historical document analysis
  • Signature verification
  • Document summarization and translation
  • Document forensics and provenance
  • Medical document analysis
  • Document analysis for social good
  • Document analysis for literature search
  • Gold-standard benchmarks and datasets

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 for four years after publication.

Contact: pc-chairs@icdar2023.org

ICDAR 2023: Call for ICDAR-IJDAR Journal Track Papers

The 17th International Conference on Document Analysis and Recognition (ICDAR 2023)
August 21-26, 2023 San José, California, USA
https://icdar2023.org/
PDF version of this call: CfP ICDAR-IJDAR Journal Track
IJDAR website: CfP ICDAR-IJDAR Journal Track

Following a tradition established at ICDAR 2019 and 2021, ICDAR 2023 will include a journal paper track that offers the rapid turnaround and dissemination times of a conference, while providing the paper length, scientific rigor, and careful review process of an archival journal.

Important Dates

Oct 31, 2022  1st round journal track paper submissions due
Jan 04, 2023  1st round journal track paper notifications
Jan 15, 2023  *Regular ICDAR proceedings paper submission deadline
Mar 15, 2023  2nd round journal track paper submissions due
May 15, 2023  2nd round journal track paper notifications

The ICDAR-IJDAR journal track invites high-quality submissions presenting original research in Document Analysis and Recognition. Journal versions of previously published conference papers or survey papers will not be considered for this special issue; such submissions can be submitted as journal-only papers via the regular IJDAR process.

Accepted papers will be published in a special issue of IJDAR, and will receive an oral presentation slot at ICDAR 2023. Authors who submit their work to the journal track commit themselves to present their results at the ICDAR conference if their paper is accepted. IJDAR’s publisher, Springer-Nature, will make accepted papers freely available for four weeks around the conference. After this, accepted papers will be available from the archival journal.

Format: Journal track papers submissions should follow the format of IJDAR submissions and the standard guidelines for the journal.

Procedure and Deadlines:
While we permit a second round of submissions for the ICDAR-IJDAR journal track for both new submissions and revised papers from the 1st round of submissions, it must be understood by all authors that the full journal review process will be required for all ICDAR-IJDAR track submissions — there is no “short cut.” Papers submitted late in the second round run a risk of the review process not completing in time. In such cases, authors should know that:
(1) The submitted paper can still continue under review as an IJDAR paper.
(2) The authors always have the option of preparing a shorter version of the paper to submit as a regular ICDAR conference paper.

Questions regarding the status of a paper that is under review for the IJDAR- ICDAR journal track should be directed to Ms. Katherine Moretti @Springer (katherine.moretti@springer.com). The guest editors have full authority to determine that the journal review process will not complete in time, and to decline submissions that arrive too late. In which case they will immediately notify the authors who can decide to leave the paper in the standard journal reviewing system or withdraw their manuscript from the journal.

Special Issue Guest Editors
ICDAR 2023 PC Chairs: Gernot A. Fink, Rajiv Jain, Koichi Kise (liaison to IJDAR), and Richard Zanibbi

Inquiries
For additional information, please email one of the editors of this special issue or consult the FAQ that will be posted on the IJDAR website.

ICDAR 2023: Call for Competitions

The 17th International Conference on Document Analysis and Recognition (ICDAR 2023)
August 21-26, 2023 San José, California, USA
https://icdar2023.org/

The ICDAR 2023 Organizing Committee invites proposals for competitions that aim at evaluating the performance of algorithms and methods related to areas of document analysis and recognition.

Important Dates

Oct 28, 2022: Competition Proposal Due
Nov 15, 2022: Competition Acceptance Notification
Dec 01, 2022: Individual Competition Websites are Live
Mar 20, 2023: Suggested deadline for competition participants
Apr 10, 2023: Initial Submission of Competition Reports Deadline 
May 01, 2023: Camera-Ready Papers Due
Jul 01, 2023: Communicate Winners to Chairs
Aug 21-26, 2023: Presentation of results at ICDAR Conference

You are cordially invited to submit a proposal, that should contain the following information:

  • Contest title and abstract
  • A brief description of the competition, including what the particular task under evaluation is, why this competition is of interest to the ICDAR community, and the expected number of participants
  • An outline of the competition schedule
  • Description of the dataset to be used, and the evaluation process and metrics for submitted methods
  • The names, contact information, and brief CVs of the competition organizers, outlining previous experience in performance evaluation and/or organizing competitions

The following rules shall apply to the accepted Competitions:

  • The name of competition must be standardized by starting with “ICDAR 2023” e.g. “ICDAR 2023 Competition on …” or “ICDAR 2023 … Competition.”
  • Datasets used in the competitions must be made available after the end of the competitions. Specifically, the training data and ground truth must be publicly released and there must be a way to evaluate performance on a test set. This could take the form of an evaluation server, or the test data, ground truth, and evaluation script could be made publicly available. In principle, the organizers should submit the dataset to IAPR TC10 or TC11.
  • Evaluation methodologies and metrics used must be described in detail so that results can be replicated later. Evaluation scripts must be released afterwards.
  • Each competition has to be presented with a poster at a prominent place at the conference venue, and selected competitions will get the chance to be presented orally in the dedicated session mentioned above.
  • Competitions must have a sufficient number of participants to be able to draw meaningful conclusions.
  • Reports (full papers) on each competition will be reviewed and, if accepted (the competition ran according to plan, attracted a minimum level of participation and is appropriately described), will be published in the ICDAR 2023 conference proceedings.
  • Participants should not have access to the ground-truthed test dataset until the end of the competition. The evaluation should be done by the organizers.

Submission Guidelines & Inquiries

All proposals should be submitted by electronic mail to the Competition Chairs (Kenny Davila, Dimosthenis Karatzas, and Chris Tensmeyer) via:

competitions-chairs@icdar2023.org

We encourage competitions proposals with a solid plan to remain active and challenging for the community over and above ICDAR 2023.

For any inquiries you may have regarding the competitions, please contact us via above email.



Tenure-Track Assistant Professor Position (Computer Vision)

Rochester Institute of Technology, NY, USA

The Department of Computer Science at the Rochester Institute of Technology invites applications for a full-time tenure-track assistant professor position in the area of computer vision. Successful applicants are expected to contribute to the scholarship of the department and college through externally funded research and through teaching and mentoring of BS, MS, and PhD students.

Apply online: https://careers.rit.edu/faculty. Keyword Search: 7235BR.

Please submit the following:

  • A cover letter addressing the required qualifications for this position.
  • A curriculum vitae.
  • A research statement.
  • A teaching statement.
  • A diversity statement.
  • The names and contact information of three references.

You can contact the search committee with questions on the position at: cs-facsearch@rit.edu. For guaranteed consideration, candidates should apply by December 1, 2022.

Required minimum qualifications:

  • PhD in computer science or closely related discipline by the date of appointment.
  • Ongoing strong publication record and potential for obtaining external funding in computer vision.
  • Commitment to and experience in teaching and mentoring BS, MS, and PhD students in computer science.
  • Ability to contribute in meaningful ways to the RIT’s continuing commitment to cultural diversity, pluralism, and individual differences.
  • Ability to communicate effectively in English.

Computer Science (https://cs.rit.edu) is the largest department at RIT. Our student-centered programs are home to nearly 1,400 students pursuing BS, MS, BS/MS, and PhD degrees. Student employment rates upon graduation are over 98%, often with leading technology companies. Our innovative problem-based introductory programming sequence has been continuously updated, in part through research projects funded by the National Science Foundation (NSF). The BS in Computer Science program at RIT is ranked 54th in the U.S. News and World Reports 2022 ranking of Best Undergraduate Computer Science Programs. Our faculty publish in top-tier venues, and contribute to leading conferences and journals. Funded research is carried out in the areas of artificial intelligence, computing education, data science, distributed systems, graphics and visualization, pervasive computing, programming languages, security, and theory (https://rit.edu/computing/department-computer-science). Students at all levels participate in research projects, including through NSF-sponsored undergraduate research programs. Our PhD students have made meaningful contributions to their respective areas, and gone on to secure excellent positions in industry and academia. Faculty are encouraged to develop new courses and teach in their area of interest and have a low teaching load with capped class sizes.

The Golisano College of Computing and Information Sciences prepares students to change the world through computing; GCCIS is home to the departments of Computer Science, Software Engineering, Computing Security, School of Information, and the School of Interactive Games and Media. The college’s PhD program in Computer and Information Sciences was ranked 63rd in the U.S. in the CSRankings listing of top computing doctoral programs. The college has over 130 full-time faculty and more than 3,600 undergraduate and 950 graduate students. RIT is an interdisciplinary research hub, with research groups and communities encompassing a range of domain areas, including the Global Cybersecurity Institute (https://rit.edu/cybersecurity), RIT’s Personalized Healthcare Technology initiative (https://pht.rit.edu), the Center for Human-Aware Artificial Intelligence (https://rit.edu/chai), the Center for Advancing STEM Teaching, Learning and Evaluation (https://rit.edu/castle/), the Media Arts Games Interaction Creativity (MAGIC) Center (https://magic.rit.edu), the Center for Computational Relativity and Gravitation (https://ccrg.rit.edu/), the Golisano Institute for Sustainability (https://rit.edu/sustainabilityinstitute/).

Postdoctoral Research Position on Document Intelligence and Privacy Preserving Learning

The Computer Vision Center (CVC), Barcelona, has a vacancy for a postdoc to work at the frontier between document intelligence and privacy preserving learning.

The position is linked to the European Lighthouse on Secure and Safe AI (ELSA) project https://elsa-ai.eu/, funded by European Union’s Horizon Europe research and innovation programme.

The successful candidate is expected to contribute to the design and development of AI solutions for document understanding, and in particular on Document Visual Question Answering systems, employing privacy preserving techniques and infrastructures set up by the ELSA project.

The candidate is expected to have extensive experience in at least one of: document intelligence and/or private and robust collaborative learning (differential privacy, federated learning), and an appetite to learn.

All applications must include a full CV in English including contact details and a Cover Letter with a statement of interest in English.

Duration: between 30 and 36 months, depending on the start date
Salary: €40,000 annual gross, according to CVC labour categories

More information and application procedure: https://euraxess.ec.europa.eu/jobs/815190 http://www.cvc.uab.es/blog/2022/07/19/postdoctoral-research-position/



TC11 Datasets Repository (repost)

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@lrde.epita.fr )


Call for Contributions: To contribute news items, please send a short email to the editor, Andreas Fischer ([1]). 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.