[Apologies for multiple postings]
Multimedia Retrieval in CLEF
*** CALL FOR PARTICIPATION ***
ImageCLEF 2018 is an evaluation campaign that is being organized as
part of the CLEF initiative labs. The campaign offers several research
tasks that welcome participation from teams around the world.
The results of the campaign appear in the working notes proceedings,
published by CEUR Workshop Proceedings (CEUR-WS.org) and are presented
in the CLEF workshop. Selected contributions among the participants
will be invited for submission to a special section "Best of CLEF'18
Labs" in the Springer Lecture Notes in Computer Science (LNCS) of
Target communities involve (but are not limited to):
- information retrieval (text, vision, audio, multimedia, social
media, sensor data, etc.)
- machine learning, deep learning
- data mining
- natural language processing
- image and video processing
- computer vision
- question answering
*** 2018 TASKS ***
The availability of a large variety of personal devices, e.g.,
smartphones, video cameras as well as wearable devices that allow
capturing pictures, and videos in every moment of our life is creating
the need for systems that can automatically categorize, summarize and
retrieve these data. The task addresses the problems of lifelogging
data understanding, summarization and retrieval.
Organizers: Duc-Tien Dang-Nguyen (Dublin City University), Luca Piras
(University of Cagliari), Michael Riegler (University of Oslo), Liting
Zhou (Dublin City University), Mathias Lux (Klagenfurt University),
Cathal Gurrin (Dublin City University).
Interpreting and summarizing the insights gained from medical images
such as radiology output is a time-consuming task. As a consequence,
there is a considerable need for automatic methods that can
approximate this mapping from visual information to condensed textual
descriptions. The task addresses the problem of bio-medical image
concept detection and caption prediction from large training data.
Organizers: Carsten Eickhoff (ETH Zurich), Alba García Seco de Herrera
(University of Essex), Henning Müller (HES-SO).
The task is to provide tuberculosis severity score based on the
automatic analysis of lung CT images of patients. Extracting this
information from images allows to limit lung washing and laboratory
analyses to determine the tuberculosis type and drug resistances, thus
reduce antibiotics use and lower impact on the patient.
Organizers: Vassili Kovalev (Institute for Informatics Minsk), Henning
Müller (HES-SO), Vitali Liauchuk (Institute for Informatics Minsk),
Yashin Dicente Cid (HES-SO).
With the increasing access to electronic medical records, patients can
now review reports associated with their healthcare utilization. Such
access can help them better understand their conditions. Given a
medical image accompanied with a set of clinically relevant questions,
participating systems are tasked with answering the questions based on
the visual image content.
Organizers: Sadid Hasan (Philips Research Cambridge), Yuan Ling
(Philips Research Cambridge), Oladimeji Farri (Philips Research
Cambridge), Henning Müller (HES-SO), Matthew Lungren (Stanford
University Medical Center).
*** IMPORTANT DATES ***
(may vary depending on the task)
- Task registration opens: November 8, 2017
- Run submission: May 1, 2018
- Working notes submission: May 31, 2018
- CLEF long paper submission: May 7, 2018
- CLEF short paper submission: May 14, 2018
- CLEF 2018 conference: September 10-14, Avignon, France
*** OVERALL COORDINATION ***
Bogdan Ionescu, University Politehnica of Bucharest, Romania
Mauricio Villegas, SearchInk, Germany
Henning Müller, HES-SO, Sierre, Switzerland
On behalf of the Organizers,
Prof. Bogdan IONESCU
ETTI - University Politehnica of Bucharest
Research Center CAMPUS