| Introduction |
ImageCLEF is the cross-language
image retrieval track which is run as part of the
Cross Language Evaluation Forum
(CLEF) campaign. This track evaluates retrieval of images described by text
captions based on queries in a different language; both text and image matching
techniques are potentially exploitable. A preliminary flyer for ImageCLEF 2007
can be downloaded here
ImageCLEF
2006 offers tasks for system-centered evaluation of image retrieval and
automatic annotation systems:
In 2007,
the user-centered evaluation tasks will be included in the
interactive CLEF track (iCLEF).
It is expected that Content-Based Image
Retrieval (CBIR) will be used for the medical tasks and a base system will be
made publicly accessible. The tasks offer different and challenging retrieval problems for
cross-language image retrieval. The first task is also envisaged as an entry
level task for newcomers to CLEF and to CLIR.
The main goals of ImageCLEF are to
investigate the effectiveness of combining text and image for retrieval,
collect and provide resources for benchmarking image retrieval systems and
promote the exchange of ideas which will lead to improvements in the
performance of retrieval systems. ImageCLEF is coordinated
by the University of Sheffield and the University and University Hospitals of
Geneva.
Further
contributors to ImageCLEF include Oregon Health and Science University (OHSU), Aachen University of
Technology (RWTH) and the MUSCLE Network
of Excellence (NoE). For more information see the
main ImageCLEF website.
Similar to 2006, there will be another
MUSCLE/ImageCLEF
workshop prior to CLEF.
|
| What to do if interested in
participating |
You can register for
ImageCLEF 2007 here (under
registration). For more specific information about any aspect of
ImageCLEF or the tasks, please contact Paul Clough or
Henning
Müller.
Once you have registered with CLEF and filled in the appropriate
copyright and declaration forms you will be able to download the data
collections. The data can be downloaded from individual task websites.
|
| Image
collections |
Four sets of image collections
will be used in 2006:
- ImageCLEFmed collection made available by
the University and University Hospitals Geneva in collaboration with Oregon
Health and Science University (OHSU).
- IRMA database of 10,000 medical
images, copyright the IRMA group, Aachen University of Technology (RWTH),
Germany (use is currently limited to the ImageCLEF competition). These images
are from the IRMA
project.
|
| Important
dates |
| |
|
| Registration
opens |
15
January 2007 |
| Data
release |
from 15
February 2007 |
| Topics
release |
from 15
March 2007 |
| Submission of
runs |
15 May
2007 |
| Release of
results |
from 15
July 2007 |
| Submission of paper
for working notes |
15 August
2007 |
| MUSCLE
workshop |
18
September 2007 |
| Workshop (in
conjunction with ECDL2007 in Budapest,
Hungary) |
19-21
September 2007 |
| |
|
|
NOTE: Please refer to
specific task web pages for any changes to this schedule.
| Organisers of
ImageCLEF |
Henning Mueller is overall organiser of ImageCLEF 2007. Several
other individuals and research groups are also involved in providing and
running different ImageCLEF tasks. For information about the tasks, please
contact the task organisers listed below:
General ad-hoc bilingual
search task
Michael Grubinger,
School of Computer Science and
Mathematics, Victoria University, Australia (michael.grubinger@research.vu.edu.au)
Allan
Hanbury, Vienna University of Technology, Austria (hanbury@prip.tuwien.ac.at)
Paul
Clough, Department of Information Studies, University of Sheffield, UK (p.d.clough@sheffield.ac.uk)
Interactive search task (iCLEF)
Julio Gonzalo, NLP Group, UNED,
Spain (julio@lsi.uned.es)
Paul
Clough, Department of Information Studies, University of Sheffield, UK (p.d.clough@sheffield.ac.uk)
Jussi Karlgren, Swedish Institute of
Computer Science, Sweden (Jussi.Karlgren@sics.se)
Medical image
retrieval
Henning Mueller,
University and University Hospitals of Geneva, Switzerland
(henning.mueller@sim.hcuge.ch)
William Hersh,
Oregon Health and Science University, USA (hersh@ohsu.edu)
Automatic image annotation
Thomas Lehmann, IRMA group, Aachen
University of Technology (RWTH), Germany (lehmann@computer.org)
Thomas
Deselaers, Human Language Technology and Pattern Recognition Group,
Computer Science Department, RWTH Aachen University, Aachen, Germany (deselaers@i6.informatik.rwth-aachen.de)
Allan Hanbury, Vienna
University of Technology, Austria (hanbury@prip.tuwien.ac.at)
|
|
