============================================================================ IAPR TC-11 Newsletter January 2016 http://www.iapr-tc11.org ========== Contents ======================================================== * Message from the Editor * Dates 'n' Deadlines - ICPR 2016, Cancun, Mexico April 4 (http://www.icpr2016.org/) - ICFHR 2016, Shenzen, China April 30 (http://www.nlpr.ia.ac.cn/icfhr2016) * New and Recently Published Datasets * First Announcement: - First IAPR Summer School on Document Analysis: Large Scale Document Understanding (Endorsed by TC10 and TC11), New Delhi, India, December 12-16, 2016 * Call for Papers - 14th Int. Conf. on Document Analysis and Recognition (ICDAR) 2017 Kyoto, Japan, November 10-15, 2017 (http://u-pat.org/ICDAR2017) * Calls for Participation: - Tutorials at the Int. Workshop on Document Ananlysis Systems, DAS 2016 Santorini, Greece, April 11, 2016 (http://www.primaresearch.org/das2016/tutorials) - International Document Information Processing School (IDIPS), Samos, Greece, 4-8 July, 2016 (http://samosweb.aegean.gr/idips2016/) - Handwritten Scanned Document Retrieval Challenge @ ImageCLEF 2016 (http://imageclef.org/2016/handwritten) * Job Advertisements - 3 Postdoctoral Fellow Positions at the CVC (Barcelona) (repost) * Call for Dataset Submissions * Call for Contributions ============================================================================ ========== Message from the Editor ========================================= Welcome to the first edition of our newsletter in 2016. This edition brings to you the first announcement of a new joint activity of TC-10 (Graphics Recognition) and TC-11 (Reading Systems), namely the First IAPR Summer School on Document Analysis. After an open Call for Hosting Proposals issued in April 2015, the TC-10 and TC-11 Education Officers, who are my colleague Alicia Fornés and myself, together with an advisory committee of international experts evaluated the proposals submitted. Now we are happy to announce that the First IAPR Summer School on Document Analysis - focussing on Large Scale Document Understanding - will be held in New Delhi, India in December 2016 (yes, we will call it "Summer School" anyway This newsletter also contains the first Call for Papers for the 14th International Conference on Document Analysis and Recognition (ICDAR), which will be held in Kyoto, Japan in November 2017, as well as the announcement of the Tutorials that will be given at DAS 2016 and that can be attended free of charge by all DAS participants. Furthermore, you will find below the Calls for Participation for the International Document Information Processing School (IDIPS) 2016, and for the Handwritten Scanned Document Retrieval Challenge that will be organized in the context of ImageCLEF 2016. 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): ---------------------------------------------------------------------------- * BMVC 2016, York, UK September 19-22 2016 May 9 (http://bmvc2016.cs.york.ac.uk/) * ICFHR 2016, Shenzen, China October 23-26, 2016 April 30 (http://www.nlpr.ia.ac.cn/icfhr2016) * ICPR 2016, Cancun, Mexico December 4-8, 2016 April 4 (http://www.icpr2016.org/) * ICDAR 2017, Kyoto, Japan November 10-15, 2017 April 16, 2017 (http://u-pat.org/ICDAR2017) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - * DRR 2016, San Francisco, USA Feb 15-18, 2016 - passed - (http://drr2016.loria.fr) * Int. Conf. on Nat. Sci. Tech. in February 29 - - passed - Manuscript Analysis, Hamburg, Germany - March 2, 2016 (http://www.manuscript-cultures.uni-hamburg.de/natural_sciences_2016.html) * DAS 2016, Santorini, Greece April 11-14, 2016 - passed - (http://www.primaresearch.org/das2016) * CVPR 2016, Las Vegas, United States June 26-July 1, 2016 - passed - (http://www.pamitc.org/cvpr16/) ============================================================================ ========== New and Recently Published: TC-11 Datasets ====================== For a list of all datasets available visit: http://www.iapr-tc11.org/mediawiki/index.php/Datasets_List ============================================================================ ========== Announcement: First IAPR Summer School on Document Analysis ===== CALL FOR PARTICIPATION First IAPR Summer School on Document Analysis: Large Scale Document Understanding (Endorsed by TC10 and TC11) Dates: 12th to 16th December 2016. Location: IIT Delhi, New Delhi, India Organised by: IIT Delhi & IUPRAI 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. The school will focus on following core areas: * features, representation and indexing for large document collections * content representation and manipulation * Information and document retrieval * machine learning and analytics for large document repositories The school will be conducted by world-renowned and experienced researchers. It will have (i) Tutorial talks; (ii) Focused research seminars; (iii) Poster session presenting research of the participants; (iv) Hands-on Exercises; (v) Industrial Presentations. LOCATION Location of the event will be the beautiful campus of IIT Delhi where the participants will have enough opportunity to interact with each other as well as renowned speakers during the sessions, food breaks, evening social events etc. IIT Delhi has a serene green campus of about 300 acres with all modern amenities. PARTICIPATION The school is open to young researchers from across the world. Registration (400 Euro) will cover attendance, proceedings, dinners, coffee breaks and social events. Organisers will arrange for subsidized bed and breakfast accommodations at the rate of about 30 euro per head per night. Participants can apply with a short CV and one page write-up (10 pt.) on their proposed research presentation to Santanu Chaudhury by 30th June, 2016. PROGRAM CHAIRS Venu Govindaraju, University of Buffalo, USA Santanu Chaudhury, IIT Delhi, India C. V. Jawahar, IIIT Hyderabad, India ============================================================================ ========== Call for Papers: ICDAR 2017 ===================================== First Call for Papers 14th International Conference on Document Analysis and Recognition ICDAR 2017 @ Kyoto, Japan November 10-15, 2017 http://u-pat.org/ICDAR2017/ [ICDAR Meets Kyoto in Best Season] The 14th International Conference on Document Analysis and Recognition (ICDAR 2017) will be taking place in Kyoto, Japan. Kyoto is one of the most popular destinations in Japan. Approximately 50 million people visit there every year. Kyoto had been the imperial capital of Japan for more than 1000 years and is known as a city of UNESCO World Heritage, in which about 20% of Japan's National Treasures and 14% of Important Cultural Properties exist. ICDAR2017 will be taking place in the "Autumn leaves" season, in which green leaves change their color to yellow and red gradually and eventually fall. Many people fascinated by the beautiful scenery visit Kyoto in the season. ICDAR2017 will provide an opportunity to the participants to access the best season in Kyoto. [Topics of Interest] include, but are not limited to: - Character Recognition - Handwriting Recognition - Graphics Recognition - Document Image Analysis - Document Understanding - Document Analysis Systems - Camera-Based Document Image Analysis - Document Databases and Digital Libraries - Multimedia Document Analysis - Forensic Document Analysis - Historical Document Analysis - User Interface - Performance Evaluation - Novel Applications [Organization] - Honorary Chairs Prof. Kazuhiko Yamamoto (Gifu University, Japan) Prof. Masaki Nakagawa (Tokyo University of Agriculture and Technology, Japan) - General Chair Koichi Kise (Osaka Prefecture University, Japan) - Executive Co-Chairs Shinichiro Omachi (Tohoku University, Japan) Seiichi Uchida (Kyushu University, Japan Masakazu Iwamura (Osaka Prefecture University, Japan) - Program Committee Chairs C.V. Jawahar (IIIT Hyderabad, India) Daniel Lopresti (Lehigh University USA) Dimothenis Karatzas (CVC, Spain) - Workshop Chairs Umapada Pal (Indian Statistical Institute, India) Michael Blumenstein (Griffith University, Australia) - Competition Chairs Jean-Marc Ogier (University of La Rochelle, France) Marcus Liwicki (DFKI, Germany & University of Fribourg, Switzerland) - Tutorial Chairs Simone Marinai (University of Florence, Italy) Josep Llados (CVC, Spain) - Publication Chairs Wataru Ohyama (Mie University, Japan) Seiji Hotta (Tokyo University of Agriculture and Technology, Japan) Kengo Terasawa (Future University Hakodate, Japan) - Publicity Chairs David Doermann (DARPA, USA) Cheng-Lin Liu (Chinese Academy of Sciences, China) Gernot Fink (TU Dortmund University , Germany) Tomo Miyazaki (Tohoku University, Japan) - Sponsorship Chairs Andreas Dengel (DFKI, Germany) Hisashi Ikeda (Hitachi, Japan) - Finance Chair Masakazu Iwamura (Osaka Prefecture University, Japan) [Important Dates (tentative)] - Workshops and Competitions Proposal Due: November 1, 2016 - Tutorials Proposal Due: December 15, 2016 - Papers Submission Deadline: April 1, 2017 Acceptance Notification: July 1, 2017 Camera Ready Papers Due: September 1, 2017 [Inquiries] icdar2017-inquiry *** m.cs.osakafu-u.ac.jp (please replace *** with atmark) ============================================================================ ========== Call for Participation: Tutorials at DAS 2016 =================== We are happy to announce that the following two half-day tutorials will take place during the 12th Int. Workshop on Document Analysis Systems (DAS 2016) in Santorini. The tutorials will take place on April 11, the first day of the workshop. Registered participants can attend free of charge. Tutorial 1: "Scene-Text Localization, Recognition, and Understanding" Albert Gordo (Xerox Research Center Europe) and Lluís Gómez i Bigordà (Computer Vision Center, Universitat Autonòma de Barcelona) Abstract: During the last few years, the computer vision and document analysis communities have started giving attention to tasks related to text localization and recognition in natural images (also referred to as scene-text or text-in-the-wild), particularly after the seminal works of Wang et al. More recently, and steered by the current deep learning renaissance, architectures based on convolutional neural networks and recurrent neural networks have shown outstanding results on localization and recognition tasks, and have allowed researchers to approach more challenging problems such as text understanding in natural images. This tutorial has three main objectives: first, to familiarize the audience with the problem of localization, recognition, and understanding of text in natural images, highlighting the similarities and differences between them and the same tasks performed on document images. Second, to provide some details about the techniques that are showing the largest potential for current and future research in the topic, and that could be easily transferred or adapted back to the document analysis domain. Third, to present to the audience open-source libraries that implement some of the current state-of-the-art methods. Tutorial 2: "Tesseract Blends Old and New OCR Technology" Ray Smith (Google Inc) Abstract: This tutorial will cover the algorithms, design and implementation of the open source OCR engine known as Tesseract. Designed largely in secret, the methods used in Tesseract are not well known, yet it remains a formidable force in OCR, and continues to improve. The layout analysis was second in the 2009 ICDAR competition, it supports more than 100 languages, including Chinese, and several Indic languages, and recent changes have allowed easy plugin of new classifiers, including a new Deep LSTM addition. Cheng-Lin Liu Dimosthenis Karatzas (DAS 2016 Tutorials Chairs) ============================================================================ ========== Call for Participation: IDIPS 2016 ============================== We are pleased to announce the 4th annual IDIPS Summer school is now taking applications for summer 2016. This year IDIPS will take place on the island of Samos, Greece, 4-8 July, 2016. IDIPS, the International Document Information Processing School, this year is expanding to include National Language Processing (NLP). Document Analysis Systems (DAS) nowadays use more NLP in order to improve their precision. The two fields share common problems and even techniques. It is our intention to prepare young researchers of both fields to combine knowledge from NLP and DAS in order to solve modern problems. IDIPS will include lectures of basic and advanced knowledge from the fields of DAS and NLP, as well as from Machine Learning, very useful for both fields. The cost is 625 Euros (Early Registration) and includes lodging. Registration forms are available at http://samosweb.aegean.gr/idips2016/. The due date for early registration is 30 April 2016. We look forward to seeing you or your students there. ORGANIZING COMMITTEE Elisa H. Barney Smith, Boise State University, USA Walter Daelemans, University of Antwerp, Belgium Daniel P. Lopresti, Lehigh University, USA Ergina Kavallieratou, University of the Aegean, Greece Jean-Marc Ogier, Université de La Rochelle, France Umapada Pal, Indian Statistical Institute, India Athanassios Skodras, University of Patras, Greece Efstathios Stamatatos, University of the Aegean, Greece Seiichi Uchida, Kyushu University, Japan ============================================================================ ========== Call for Participation: HWS Doc. Retrieval @ ImageCLEF 2016 ===== Call for Participation Handwritten Scanned Document Retrieval Challenge @ ImageCLEF 2016 http://imageclef.org/2016/handwritten We cordially invite you to participate in a new evaluation campaign aimed at the development of systems for textual-query retrieval from historical handwritten collections. The evaluation will be characterized by the following key challenges: - Multi-word queries. - Finding broken words due to hyphenation. - Queries with words not seen in the training data. - Queries with zero relevant results. - Results in the transitions between pages. - Proximity searching. The evaluation tries to allow easy participation from different research communities, with the aim of having synergies and providing different ideas and solutions to the problems being addressed. In particular, we hope to have participation at least from groups working on: handwritten text recognition, image-based keyword spotting and text retrieval. The primary training/development information will consist in the original page images and transcripts. This can be directly used by researchers working on keyword spotting. Moreover, word bounding boxes will be provided for the convenience of groups that work on query-by-example keyword spotting. In addition to the original page images and transcripts, plain text n-best recognition lists will be provided, to allow easy participation of researchers that normally work with text only. The participants will have a chance to submit a paper describing their systems, which will be peer reviewed and if accepted, published in the CEUR-WS proceedings. Furthermore, the groups of the best performing systems will be invited to give an oral presentation at CLEF 2016 and others will be given the option of presenting a poster. Attendance to CLEF is not mandatory (though recommended) for participating or the papers being published. This challenge is being organized as part of ImageCLEF, a lab of CLEF 2016 (http://clef2016.clef-initiative.eu). Any questions or comments you may have, feel free to contact us. For more details on the evaluation please visit http://imageclef.org/2016/handwritten Schedule: 15.11.2015: registration opens (until 22.04.2016) 16.12.2015: release of training/development data 15.03.2016: release of test data 01.05.2016: deadline for submission of runs by the participants 15.05.2016: release of processed results by the task organizers 25.05.2016: deadline for submission of working notes papers 17.06.2016: notification of acceptance of the working notes papers 01.07.2016: camera ready working notes papers 05.-08.09.2016: CLEF 2016, Évora, Portugal Organizing Committee: Universitat Politècnica de València, Spain - Joan Puigcerver - Alejandro H. Toselli - Joan Andreu Sánchez - Enrique Vidal - Mauricio Villegas ============================================================================ ========== Jobs: Postdoctoral Positions at the CVC ============= (repost) == THREE POSTDOCTORAL FELLOW POSITIONS AT THE COMPUTER VISION CENTER (BARCELONA) The project P-SPHERE, coordinated by the Universitat Autònoma de Barcelona (UAB) and with participation of UAB-CIE member centers, has received funding from the latest COFUND-2014 call. The COFUND program is part of the European Commission´s Marie Sklodowska-Curie actions. The Computer Vision Center (CVC), as part of the UAB-CIE sphere, offers 3 post-doc positions in the following research lines. * Holistic interpretation of urban scene imagery * Ultimate color descriptor including multiple light effects * Human pose recovery and behavior analysis The call will be open from November 2nd 2015 to February 2nd 2016. For the position on "Holistic interpretation of urban scene imagery", of particular interest is the interplay between visual and textual content in a scene image, and to what extent such modalities can work synergistically towards urban scene imagery interpretation. For more information and to submit your application, please visit the official website. http://www.uab.cat/psphere/ ============================================================================ ========== Call for Dataset Submissions ==================================== We would like to remind you that the TC10 and TC11 welcome contributions of new datasets or other resources related to the community. We would like to particularly encourage authors of articles that introduce new datasets, software or other material to submit such material to TC11 for hosting. Please check the TC11 site on information about how to submit datasets for archiving ( http://www.iapr-tc11.org/mediawiki/index.php/Datasets) also feel free to contact Marcus Liwicki, the TC11 dataset curator, for any doubts you might have on the process. Marcus Liwicki, TC-11 Dataset Curator liwicki@dfki.uni-kl.de ============================================================================ ========== 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 ============================================================================