IAPR TC11 Newsletter 2023 07

From TC11
Jump to: navigation, search
IAPR logo.gif Tc-11 Logo v2 72dpi.png

July, 2023



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

  • Message from the Editor
  • Dates and Deadlines
    • Upcoming Conferences and Events
  • 3 Postdoctoral Positions in Computer Vision, Machine Learning and Document Analysis in Luleå Sweden
  • Call for Participation -- PFL-DocVQA Competition
  • Datasets
    • TC11 Datasets Repository



Dear TC11 members,

This issue contains new job offers: 3 post-doc positions at Luleå, Sweden. You will also find a call for participation in the PFL-DocVQA competition (Privacy Preserving Federated Learning Document VQA), which will be one of NeurIPS 2023 competitions. Make sure to check the deadlines of the different calls and job offers before you leave on summer vacation!

Enjoy your summer!

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 Twitter (iapr_tc11): https://twitter.com/iapr_tc11



Upcoming Conferences and Events

2023 and 2024

  • ICDAR 2023. San José, USA (August 21-26, 2023)
  • TPDL 2023. Zadar, Croatia (September 26-29, 2023)
  • ACPR 2023. Kitakyushu, Japan (November 5-8, 2023)
  • ICDAR 2024. Athens, Greece (August 30 - September 4, 2024)
  • ICPR 2024. Kolkata, India (December 01-05, 2024)



Are you interested in doing cutting edge research in computer vision, machine learning and document analysis? We are excited to announce that we have three postdoctoral positions available in the Machine Learning group at Luleå Technical University (LTU), Sweden.

We are looking for applicants who are ambitious and creative, who have a Ph.D. thesis, strong academic publications, and who want to contribute to cutting edge research in this area.

Project:
Research will be conducted in Machine Learning, especially Deep Learning, for applications in the areas of computer vision, document analysis and blueprint analysis. Potential areas include unsupervised learning, one-shot learning and use of homomorphic encryption. Work is in collaboration with Professor Elisa Barney.

These positions & scholarships are funded by foundation grants instead of a research contract, and thus there is considerable flexibility in the exact projects to be conducted. In the application the candidate should propose topics that mesh with work already in progress or recently completed by Prof. Barney. The Post-Doc is still expected to strongly participate in development and acquisition of future project funding.

Qualifications:
Applicants must have a PhD or a foreign degree equivalent to a PhD in computer science, computer engineering, electrical engineering or a closely related field. A doctoral degree awarded no more than five years before the application deadline provides a useful qualification. Experience and demonstrated background in computer vision, document analysis, signal and image processing and statistics are desired qualifications. We are looking for enthusiastic candidates capable of conducting state-of-the-art research as demonstrated through a record of peer reviewed publications. The candidate will ideally also have some experience in international research project collaboration. We expect candidates to have a good knowledge of English both in speech and writing and have the capacity to perform independently as well as in teams. As LTU is very strong in application-oriented research, industrial experience is very welcome. The Machine Learning group is very diverse and welcomes diverse applicants.

Logistics:
The postdoc positions are for two years with placement in Luleå, starting in Fall/Winter 2023.

The positions are from two separate funding sources, so there are two application portals:

Applicants may apply to both.
- Position 1 (1 opening) is a salaried position which comes with Swedish benefits

  • Position 2 (2 openings) is a scholarship. This has a slightly higher salary than Position 1, but does not participate in the Swedish retirement system.

Both produce income above the average net income in the area.

Closing date: 31 August 2023

About the Department, University and Region:
Luleå Technical University is experiencing strong growth with world-leading competence in several research areas. We shape the future through innovative education and ground-breaking research results, and based on the Arctic region, we create global social benefit. Our scientific and artistic research and education are conducted in close collaboration with international, national and regional companies, public actors and leading universities. LTU offers well-equipped laboratory facilities for performing research and a good academic network in Sweden and abroad.

The city of Luleå is located on the Gulf of Bothnia (northern Baltic Sea) a couple of hours from the Arctic Circle and the border with Finland. In the summer we have the midnight sun. In the winter you will be able to see the northern lights. Luleå is ideal for outdoor enthusiasts who want to get out and explore with a superb infrastructure of bicycling roads, and in winter our Ice Road. The city has an excellent public transportation system and nearly a dozen flights daily to the south. There are plenty of top notch restaurants and cultural activities in Luleå too.



NeurIPS 2023 Privacy Preserving Federated Learning Document VQA Competition

The Privacy Preserving Federated Learning Document VQA (PFL-DocVQA) seeks new privacy-preserving solutions for fine-tuning multi-modal language models for document understanding on distributed data.

The participating teams will create efficient federated learning solutions to fine-tune a pre-trained Document Visual Question Answering (DocVQA) model on the provided dataset with privacy guarantees.

The challenge is focused on a new domain, that of invoice processing, where both vision and language modalities are important. A large scale dataset is provided, along with baseline methods that participants can build on.

The competition is structured in 2 different tracks: 1. Federated Learning only, and 2. Federated Learning + Privacy-preserving.

The competition is organized in the context of the “European Lighthouse on Safe and Secure AI” (ELSA) Project (https://elsa-ai.eu/).

Competition Website
https://benchmarks.elsa-ai.eu/?ch=2&com=introduction

Important Dates

  • November 15, 2023: Winning teams announced.
  • November 1, 2023: Privacy proof reports due for Track 2 participant teams.
  • October 27, 2023: End of the competition. Submission data deadline.
  • June 30, 2023: Release of training and validation splits.
  • June 15, 2023: Competition registration opens.

Organizers

  • Dimosthenis Karatzas, Rubèn Tito, Mohamed Ali Souibgui, Khanh Nguyen, Ernest Valveny, Josep Lladós - Computer Vision Center, Universitat Autonoma de Barcelona, Spain
  • Raouf Kerkouche, Mario Fritz - CISPA Helmholtz Center for Information Security, Germany
  • Kangsoo Jung - French Institute for Research in Computer Science and Automation (INRIA), France
  • Marlon Tobaben, Joonas Jälkö, Antti Honkela - University of Helsinki, Finland
  • Vincent Poulain, Aurelie Joseph - Yooz, France

Contact
For any queries about this challenge, please contact info_pfl@cvc.uab.cat.



TC11 Datasets Repository

Where to share datasets

Did you know it? We have two official places for datasets:
- Our historical platform for storage and listing: http://datasets.iapr-tc11.org

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, [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.