Drawings and abstract Imagery: Representation and Analysis (DIRA)
ECCV 2022, Tel Aviv, Israel
24 October 2022
Embedded Files
Welcome to the second edition of the workshop on
Welcome to the second edition of the workshop on
Drawings and abstract Imagery: Representation and Analysis (DIRA)!
Drawings and abstract Imagery: Representation and Analysis (DIRA)!
Illustrations, drawings, technical diagrams, and charts can communicate difficult concepts very quickly to humans. This type of visual information is prevalent in technical, scientific, and scholarly publications; as well as instruction manuals, textbooks, and infographics in popular media. However, many open challenges in computer vision for automatically processing this visual data remain. These abstract images have very different properties from natural images; for example, informative pixels are sparse, while the shape and spatial information are more important than color, texture, and shading which dominate natural images. While deep learning methods are quite successful in object detection and content-based retrieval in natural images; it is not clear when these approaches will transfer successfully to these much sparser abstract drawings.
The DIRA workshop aims to bring together researchers from both industry and academia who are working in diverse areas of research in the representation, analysis, and applications of abstract images, such as illustrations, drawings, technical diagrams, charts, and plots. The goal of the workshop is to explore and highlight technical challenges, insights, and solutions that exist in representation, information extraction, semantic understanding, content-based retrieval, question-answering, and various other topics pertaining to the representation and analysis of abstract images, which has traditionally lagged behind progress in their natural image counterparts.
The DIRA workshop will also host a data competition focused on abstract drawing retrieval on the DeepPatent dataset to encourage increased research and engineering activity in this field.
We hope to see you in Tel Aviv or Online!
News:
Workshop taking place live on Monday, October 24 at the David Intercontinental, Salon I
Schedule now posted (check below in case of any changes).
The DIRA Data Challenge is online on CodaLab!
Call for papers -- See below!
DIRA workshop has been accepted for a full-day hybrid event at ECCV 2022. We will accept both short and full-length papers.
Invited Speakers
Invited Speakers
Schedule
Schedule
Monday, October 24, 2022
David Intercontinental, Salon I
Remote participation instructions will be provided to registrants.
All times are local to Tel Aviv (GMT+3)
Organizers
Organizers
Research Scientist,
Adobe Research
Adobe Research
Ph.D. Student,
UCL, London
UCL, London
Postdoctoral Researcher,
Los Alamos National Lab
Los Alamos National Lab
Assistant Professor,
Colorado College
Colorado College
Call for Papers
Call for Papers
The DIRA workshop is currently soliciting papers describing new work in the following subject areas, as well as any other subject relevant to automated understanding of sparse images
Image Analysis
Image Segmentation
Semantic Image Understanding
Geometric Deep Learning
Sparse Machine Learning Models
Information Retrieval for Technical Documents
Knowledge Graph Construction
Optical Character Recognition
Feature Extraction
Multimodal Machine Learning
Plagiarism Detection
Additionally, the workshop seeks dataset papers describing new datasets in the subject areas of:
Technical Diagrams
Illustrations
Plots and Charts
Scientific Reports
Patents
Submission link will be available soon.
Submission Guidelines
All submissions will be handled electronically via the CMT Website and following the procedures required by ECCV. Full papers submissions are double-blind. Full papers will be published in the ECCV Workshop Proceedings; and are a minimum of 5 pages and a maximum of 14 pages in the ECCV style, with cited references allowed on additional pages. Please refer to the following site and files for detailed formatting instructions:
LaTeX Templates (tar): eccv2022AuthorKit.tgz
LaTeX Templates (zip): eccv2022AuthorKit.zip
Short papers are a maximum of 4 pages and will not appear in the published proceedings. They will be selected based on relevance to the workshop and quality as judged by the organizing committee.
Important Dates:
Important Dates:
Paper submission deadline (Full papers): July 15, 2022 (https://cmt3.research.microsoft.com/DIRA2022/)
Paper submission deadline (Extended Abstracts): August 1, 2022 (https://cmt3.research.microsoft.com/DIRA2022/)
Notification to Authors: August 15, 2022
Camera-ready submission deadline: August 22, 2022
All submission dates refer to 11:59pm PDT (Pacific Daylight Time) on the given date.
Page updated
Google Sites
Report abuse