============================================================================ IAPR TC-11 Newsletter December 2016 http://www.iapr-tc11.org ========== Contents ======================================================== * Message from the Editor * Dates 'n' Deadlines - DAS 2018, [in a nice place] January 31, 2017 [extended!] (proposal for hosting) - ICDAR 2017, Kyoto, Japan March 15, 2017 (http://www.iapr.org/icdar2017) * New and Recently Published Datasets * Message from the TC-11 Chair * Call for Participation: - IAPR Summer School on Document Analysis: Document Informatics Jaipur, India, January 23-28, 2017 * Job Offers: - PhD position in Math IR/Math Recognition, Department of Computer Science, Rochester Institute of Technology, Rochester, NY - Postdoc in Machine learning, LITIS, Université de Rouen, France (repost) - 3 PhD / PostDoc positions, University of Fribourg, Switzerland (repost) * Call for Proposals: - DAS 2018: Call for Hosting Proposals (repost) January 31, 2017 * Call for Dataset Submissions * Call for Contributions ============================================================================ ========== Message from the Editor ========================================= Welcome to the last edition of our newsletter in 2016. Welcome also to the last edition that will be published by myself. All loyal readers of the newsletter will probably know that I have served as the Newsletter Editor of TC-11 for almost eight years, which feels like eternity in the digital age. Therefore, with the new election term of the TC-11 Chair that started with ICPR 2016, it is now also time to pass this job on to a new person. I hope that you liked my regular information about relevant news in the area of Reading Systems. This service will now be provided by my successor who will be introducing himself with the January edition and who I wish all the best for his new responsibility. Though I will step back as the Newsletter Editor, I will continue my service on the TC-11 Leadership Team in the recently created capacity as Education Officer. Focussing on this role, I hope to be able to even better promote the educational activities of TC-11, especially the TC-10/TC-11 Joint Summer School and the ICDAR Doctoral Consortium. There will be more changes to the TC-11 Leadership Team that Dimosthenis Karatzas, the newly elected TC-11 Chair, will explain in his message of the TC-11 Chair below. For this newsletter, I would like to draw your attention to the fact that the deadline for submitting Proposals for Hosting DAS 2018 has been extended to January 31, 2017. Furthermore, you will find below the final Call for Participation for the IAPR Summer School on Document Analysis that will take place in the last week of January 2017 in Jaipur, India. Finally, this edition also includes a Job Offer for a PhD Position at the RIT, Rochester, USA. For the upcoming Christmas Season, I would like to wish you all a quiet and peaceful time and all the best for a happy and successful New Year! Gernot A. Fink, IAPR TC-11 Newsletter Editor / Education Officer Gernot.Fink@udo.edu ============================================================================ ========== Dates 'n' Deadlines ============================================= Event/Location/Web: Event Date: Deadline (paper submission): ---------------------------------------------------------------------------- * DAS 2018, [in a nice place] Fall 2018 Januray 31, 2017 (proposal for hosting) * GCPR 2017, Basel, Switzerland September 13-15, 2017 April 8, 2017 (https://gcpr2017.dmi.unibas.ch/en/) * ICDAR 2017, Kyoto, Japan November 10-15, 2017 March 15, 2017 (http://www.iapr.org/icdar2017) * ICPRAI 2018, Montreal, Canada May 14-17,2018 Nov. 15, 2018 (http://users.encs.concordia.ca/~icprai18/index.html) * ICFHR 2018, Rochester, USA (August 6-8, 2018) TBA * ICFHR 2020, Dortmund, Germany September 8-10, 2020 TBA - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - * ASAR 2017, Nancy, France April 3-5, 2017 - passed - (http://asar.ieee.tn/) * CVPR 2017, Honolulu, Hawaii, USA July 20-27, 2017 - passed - (http://cvpr2017.thecvf.com/) ============================================================================ ========== New and Recently Published: TC-11 Datasets ====================== For a list of all datasets available visit: http://tc11.cvc.uab.es ============================================================================ ========== Message from the TC-11 Chair ==================================== After four years of steady and inspiring leadership, Koichi Kise's term as TC11 chair has drawn to an end. With him, most of the existing TC11 leadership team will also be giving way to a new generation. Speaking for the whole of the TC11 community, I would like to thank them individually for the great job they did: Koichi Kise for his steadfast commitment as a chair, Marcus Liwicki and Volkmar Frinken for contributing to the continuous growth of the TC11 datasets portal, Gernot Fink for generating the most informative newsletters with unfailing punctuality, and Masakazu Iwamura for maintaining and enriching the TC11 Web as times demanded. Their dedication becomes even more important when one considers that this was all voluntary contribution. Many thanks! We will be starting the new year with a new TC11 leadership team. I am excited and honoured to serve as the new chair, following the recommendation of the past chair, starting this month of December. I look forward to building upon the success of the past teams and accompany this evolving community with the help of a renewed leadership team. I cannot tell you just as yet what the full configuration of the team will be, but I am pleased to have two colleagues from the old team join me in the new term, assuming different positions. Masakazu Iwamura will act as the vice chair of TC11, and Gernot Fink as the Education Officer in the next term. We will be complementing this team soon with new volunteers for managing the Datasets and the Communications of the TC11. Speaking about communicating, we will try to introduce more channels, apart from the newsletter, during the next term to hear back from the community. For the time being, TC11 has already gone live on twitter and you can now follow it at @IAPR_TC11. We hope to use this channel to receive feedback and communicate interesting information in a more agile way. More changes are to come, so stay tuned! For the time being, do not forget to register for the IAPR Summer School on Document Analysis: Document Informatics (SSDA 2017) - places are running out fast! Although it will be held next month, in January 2017, it will be pretty warm in India to qualify for the "summer school" term! Also, the bids for hosting DAS 2018 are still open, and will remain so until the end of January 2017 - so I you consider hosting this emblematic event of the community, please let us know! Dimosthenis Karatzas, TC-11 Chair (dimos@cvc.uab.es) ============================================================================ ========== Call for Participation: IAPR Summer School ================== IAPR Summer School on Document Analysis: Document Informatics SSDA 2017 Endorsed by: TC10 & TC11 January, 23-28 2017 Jaipur, India SCOPE The school will provide an in-depth and objective exposure to researchers of the emerging area of understanding large scale document collections and highlight open problems in this area. With deluge of documents (in a variety of forms - images, web-pages, etc.) on the web, individual and/or collaborative information foraging from document collections have become a challenging task. Researchers are developing tools not only to understand structure of the documents but also to facilitate comprehensive interpretation of the content, may be embedded in more than one document in the form of text, table and/or graphics. In this summer school we shall address different aspects of this problem of discovering actionable insight in large document collections through tutorial level talks and research overview presentations. TOPICS * Features, representation * Indexing for large document collections * Content representation and manipulation * Information and document retrieval * Machine learning, Deep Learning * Analytics for large document repositories PARTICIPATION Limited financial support available for selected international participants. Limited seats; Register here: http://cvit.iiit.ac.in/summerschool/attend.html All participants will be allowed to make a short presentation of their research work during the school. A post-event proceedings of the selected papers will be published by springer. SPEAKERS: 1. Gernot Fink (TU Dortmund University, Germany) 2. Koichi Kise (Osaka Prefecture University, Japan) 3. Ashok Popat (Google, USA) 4. Ray Smith (Google, USA) 5. Marcus Liwicki (University of Kaiserslautern, Germany) 6. Utkarsh Porwal (Ebay, USA) 7. Lipika Dey (TCS, India) 8. Babatosh Chanda (ISI, India) 9. B. B. Chaudhuri (ISI, India) 10. Manik Varma (Microsoft Research India) 11. Pushpak Bhattacharyya (Indian Institute of Technology Patna, India) MORE INFORMATION Write to us: info.ssdi2017@gmail.com or Visit: http://cvit.iiit.ac.in/SSDA/ ORGANIZERS * Santanu Chaudhury, CEERI, PILANI * Venu Govindaraju, University at Buffalo, State University of New York * C. V. Jawahar, IIIT Hyderabad ============================================================================ ========== Job Offer: PhD Position at RIT, Rochester ======================= PhD student position in Math IR/Math Recognition * Department of Computer Science * Rochester Institute of Technology, Rochester, NY The Document and Pattern Recognition Lab (DPRL) at RIT is looking to recruit a PhD student for a project in the area of Mathematical Information Retrieval. The goal of the project is to improve search results for technical document databases (e.g., Google Scholar, CiteSeerX) using models that incorporate math, along with techniques for recognizing math written by hand (for creating search queries) and typeset/laid out in .pdf (for indexing document collections). Related publications, projects and other materials may be found online (https://www.cs.rit.edu/~dprl). Interested BSc and MSc students should submit a CV to the project lead ASAP (Richard Zanibbi, rxzvcs@rit.edu). The application deadline is January 15th (https://www.rit.edu/emcs/ptgrad/program_detail.php?id=1386), but please note that some required materials (e.g. GRE scores) may be provided later, around mid-February. ============================================================================ ========== Job Offer: PhD Positions at the CVC, Barcelona ======= (repost) = *Postdoctoral position in Machine learning * The Machine Learning team at LITIS (France) is opening a postdoctoral position for a candidate with a strong experience in Machine Learning, with application to one of the following topics : Speech Processing, Handwriting Processing, Computer Vision, or Document Image Processing. The candidate will be involved in pursuing the development of Handwriting recognition and document image processing technologies to extend the PlaIR plateform that was originally developepd for digitizing old Newspapers www.plair.univ-rouen.fr . New contributions of the candidate are expected regarding Handwriting Recognition (HWR), by combining deep optical models with deep language models. He will contribute with other members of the team to various research projects in this domain. *Scientific and technical Skills* Experimented engineer or postdoctoral candidates having a strong background in one of the following topics : Neural Networks, Deep Neural Networks, Hidden Markov MOdels, Reccurent Neural Networks, statistical langguage models, computer vision. The successful candidate should have advanced programming skills (Python, C/C++, Matlab). Experience of developping models within one of the popular frameworks such as Torch 7, TensorFLow, will be particularly appreciated. *Application* Application should include a curriculum vita, a brief statement of research interests, and the names of at least three references. *Duration*: 18 months, starting as soon as possible. *Contact *: Thierry.Paquet@univ-rouen.fr ============================================================================ ========== Job Offer: PhD / PostDoc Positions, Fribourg ========= (repost) = Positions in Historical Document Analysis in the University of Fribourg ----------------------------------------------------------------------- The Document Image and Voice Analysis (DIVA) Group at the University of Fribourg offers two positions (PhD and Post-Doc) for the duration of 2-3 years. Description of the Project In HisDoc III we target historical document classification for large amounts of uncategorized facsimiles with the intent to provide new capabilities for researchers in the Digital Humanities. In particular, we will address the task of categorizing document images with respect to content, language, script, and layout. To do so, we will leverage the expertise gained from our previous projects HisDoc and HisDoc 2.0. In HisDoc we have shown that historical Document Image Analysis (DIA) can be effectively applied to extract layout structures and textual transcriptions and in the current HisDoc 2.0 project we successfully retrieved additional paleographic information. The novel contributions of HisDoc III will be complemented by these methods to cope with large document collections. The objective of HisDoc III is twofold: (i) fundamental research on combined text- and image-based classification methods and (ii) making developed technology useful for libraries, archives, and researchers in the Humanities. The PhD applicant should focus on the first task, i.e., the classification of documents. We will study novel deep learning methods for large amounts of unlabeled text and image data. These methods will be complemented by structural approaches based on document graphs. For the combination of these diverse approaches we will investigate Multiple Classifier Systems (MCS) on the one hand and integrated neural network architectures on the other. The post-doc candidate shall combine three ideas for making methods useful for libraries: (i) novel means for reducing the needed amount of ground truth by unsupervised machine learning and alternatively bootstrapping combined with active learning; (ii) intuitive computer-assisted presentation and annotation tools; and (iii) making our systems publicly available as Web services (For the latter idea, a PhD student already working at the DIVA group will work on the technical realization of the Web services). To demonstrate the suitability of the HisDoc III research results, the candidate shall design novel computer-assisted work-flows in collaboration with an advisory board compiled of scholars, librarians and archivists. A particular focus is speeding up the generation of catalog and database entries and devising ways to present methods and results in an understandable way. Requirements The ideal candidates will have a background one of the areas of Machine Learning, Document Image Analysis, and Digital Humanities with an interest in the other areas. The PhD candidate should have some experience in unsupervised machine learning, preferably with deep neural networks. A Master Degree in Computer Science are required for enrolling in the PhD program of the University of Fribourg. The post-doc candidate should hold a PhD in one of the above-mentioned areas with an interest in the interdisciplinary field of Digital Humanities. For both positions, German and/or French language skills are beneficial for the supervision of Bachelor and Master students. Starting Date The starting date of the HisDoc III project is the beginning of January 2017. A soon start is welcome. While the duration of the PhD position is over the whole project duration (3 years), the duration of the post-doc position is flexible. Contact Applications including a motivation letter, a CV, graduation records, references, and a research statement should be sent via email to Prof. Rolf Ingold and Prof. Marcus Liwicki (rolf.ingold@unifr.ch, marcus.liwicki@unifr.ch). ============================================================================ Research Rosition in STEAM Education and Sequence Data Analysis ----------------------------------------------------------------------- The Document Image and Voice Analysis (DIVA) Group at the University of Fribourg offers a position (PhD or Post-Doc) for the duration of up to 30 months Description of the Project The educational movement of STEAM is about bringing Arts at the heart of the academic curriculum in order to cultivate creative skills of young people, alongside with the knowledge and skills they acquire in STEM fields (Science, Technology, Engineering and Mathematics). New demands raised by the global economic environment and the industry for innovation, adaptability, and flexibility highlight the need for cross-disciplinarily connected skills in the educational process, such as creativity, critical thinking, innovation and risk taking, which are expected to foster innovation and economic growth. The iMuSciCA project will directly address the current requirements in education and learning for new pedagogical methodologies and innovative educational technology tools by supporting active, discovery-based, personalized, and more engaging learning and providing students and teachers with opportunities for collaboration, co-creation and collective knowledge building. As a STEAM-oriented project, iMuSciCA aims to design and implement a suite of software tools and services on top of new enabling technologies integrated on a platform that will deliver interactive music activities for teaching/learning STEM. Enabling technologies, such as interactive pen on touchpad, 3D object design and printing, as well as new multimodal interfaces that combine advanced music generation and processing with wearable technology, will be deployed to implement a web-based workbench aiming at STEAM learning. The applicant will be responsible for the conceptualization of the iMuSciCA workbench especially in the scope of analysis of deeper learning using multi-modal streaming sensor data (gestures, eye-movements, brain-activity, ?). The technical development of the workbench takes places at various iMuSciCA partners. For the analysis, existing Toolkits, like the iMotions platform shall be combined with modern sequence learning algorithm for multi-modal data. Requirements The ideal candidates will have a background in one of the areas of sequence learning, STEAM education, and HCI development, with strong interest in the other two. Furthermore, an excellent English level is required in terms of oral and written scientific communication. The scope of the research work might be either performed in the form of a PhD thesis or postdoctoral research. Starting Date The starting date of the iMuSciCA project is the beginning of January 2017. A soon start is welcome. We would be happy if the prospective candidate can candidate can participate during the project kick-off on January 11/12. Contact Applications including a motivation letter, a CV, graduation records, references, and a research statement should be sent via email to Prof. Marcus Liwicki and Dr. Fotini Simistira (marcus.liwicki@unifr.ch, fotini.simistira@unifr.ch). ============================================================================ ========== Call for Hosting Proposals: DAS 2018 ================ (repost) == Call for Hosting Proposals for DAS 2018 --------------------------------------- Following the successful organisation of the 12th IAPR International Workshop on Document Analysis Systems in Santorini (Greece) last April, by our colleagues Apostolos Antonacopoulos and Basilis Gatos, we are now soliciting proposals for organising and hosting DAS 2018. The DAS workshop has become one of the signature events for TC-11. DAS 2018 will build on the tradition established by past DAS workshops held in Kaiserslautern, Germany (1994), Malvern, PA (1996), Nagano, Japan (1998), Rio de Janeiro, Brazil (2000), Princeton, NJ (2002), Florence, Italy (2004), Nelson, New Zealand (2006), Nara, Japan (2008), Boston, MA (2010), and Gold Coast, Australia (2012), Tours-Loire Valley, France (2014), and Santorini, Greece (2016). Individuals and groups who are interested in Document Analysis Systems are invited to submit proposals for organizing and hosting DAS 2018. The event should preferably take place in late summer/fall, but is not limited to this period. The submission deadline is January 31st, 2017. Proposals should be submitted to the TC11 chair (Dimosthenis Karatzas) and vice-chair (Masakazu Iwamura). If you already know whether you are interested in preparing a proposal, please send us your expression of interest. Note that an expression of interest is not a commitment to make a formal proposal nor an official bid. If you need further information concerning DAS, please feel free to contact us. The final selection among competing proposals will be made short after the deadline by the DAS Steering Committee, which is composed of all those who have themselves organized or contributed substantially to past DAS workshops. Dimosthenis Karatzas, TC11 Chair (dimos@cvc.uab.es) Masakazu Iwamura, TC11 Vice-chair (masa@cs.osakafu-u.ac.jp) ============================================================================ ========== Call for Contributions ========================================== This newsletter needs your support in order to provide useful information to the TC11 community. Therefore, please contribute relevant news by sending a short notice to the newsletter editor Gernot A. Fink . Such news could be the obvious announcements of conferences and workshops, job opportunities, reports on past conferences, book reviews, or anything that might be of interest to a wider audience involved in the construction of reading systems. ============================================================================ ========== Subscription Information ======================================== This newsletter is sent to subscribers of the IAPR TC11 mailing list. To manage your subscription, please visit the mailing list homepage at: https://www.jiscmail.ac.uk/cgi-bin/webadmin?A0=IAPR-TC11 The homepage for IAPR TC11 is http://www.iapr-tc11.org ============================================================================