
See also: the VAST 2008 Challenge,
and the VAST 2007 Contest
UPDATE (Dec 5th, 2006)
The
contest will continue in 2007 with similar � but of course different � dataset,
tasks and schedule.�
The data
format will remain the same so you can START NOW and use the 2006 materials to
build and test your ideas and systems.�
This year we also intend to offer a pre-processed version of the dataset
so that more people can participate as different levels.
If you
have registered to download the 2006 dataset we will notify you when the 2007
is available
We are
hoping of negotiate that the best submission be able to publish a paper in one
of the journals related to Visual Analytics.
Results
The VAST
2006 symposium has ended.��
The full result details and the solution are posted.
The
interactive session took place and was a success.
Slides of the Contest Results session are
posted.
A two-page summary about the contest
appeared in the VAST Symposium Proceedings
����������� The VAST 2006 Contest: A tale of
Alderwood,� Grinstein, G., O�Connell,
T., Laskowski, S., Plaisant, C., Scholtz, J., Whiting, M.,�
����������� Proc. of� IEEE Symposium on
Visual Analytics Science and Technology (2006) 215-216
|
First place, Corporate Category Oculus Info Inc. |
|
|
Georgia Institute of Technology |
|
|
SSS Research, Inc. |
Overview
of the event
The VAST Contest is a participation
category of the IEEE
VAST 2006 Symposium. It continues in the footsteps of the IEEE InfoVis
contests as its purpose is to promote the development of
benchmarks for visual analytics and establish a forum to advance evaluation
methods. The dataset consists mostly of news stories from Alderwood�s city
newspaper, along with some multimedia materials and background
information.� The goal is to determine if
inappropriate activities are taking place and report on hypotheses and
conclusions. Participants will have several months to prepare their
submissions.� Selected entries will
present at the conference, and some teams will be invited to participate in a
special workshop before the conference during which professional analysts will
interact with the systems and provide feedback.�
����� Georges Grinstein,
Theresa O�Connell, National
Institute of Standards and Technology
Sharon Laskowski, National Institute
of Standards and Technology
Catherine
Plaisant, HCIL,
�����
����� Mark Whiting,
�������
����� Email
the Contest Chairs
Dataset � Tasks -
Judging
INFORMATION about the dataset and tasks
>> NEW: Use the VAST BENCHMARK REPOSITORY to DOWNLOAD challenge datasets
���� Judging and scoring
methodology
Schedule and deadlines
of the 2006 contest�� (will be similar in
2007)
February 15th 2006 ����� Release of complete dataset
July 18th 2006������������� Deadline
for submission
August 14th 2006�������� Acceptance
notification
Early September�������� Camera ready
materials due� (TBA)
Oct 31st � Nov 2nd�������
IEEE VAST 2006 Symposium in
First
place entries will receive a prize and will present their work during the
contest result session at the conference. All accepted entries will be posted
after the conference on the Information Visualization Benchmark
Repository (and the VAST BENCHMARK REPOSITORY).
We
will award prizes for best entries in several categories. The judges will
decide on the exact categories based on the material received - possibilities
include "Best Overall", "Best Student Entry", and
"Most Original".
Two to four first place entries will also be invited to participate in special
interactive session at the conference. Professional analysts will work with the
developers on a new problem and data set. This will provide
"personal" feedback to the teams, a unique opportunity.
The
contest is open to all, except for the contest organizers and judges. All
categories of competitors (academic and commercial) may participate. If in
doubt, ask the contest chairs.
You
may use any existing commercial product or research prototype, and of course
you may combine tools.
We
strongly encourage teams to find partners with complementary expertise
(e.g.� groups with text analysis or
reasoning tools might want to seek partners with user interface expertise) .
At
least one author of accepted submissions must
attend the Symposium.
"Partial
answers" are acceptable but we encourage you to attempt and address all
tasks. In other words, if your tool or approach only addresses part of the
task, you can still participate in the competition.
A completed answer form, a recorded video demonstration, and
a 2-page PDF summary, all zipped into one or more files.
We
provide an answer form template so that your
answers follow a consistent format to facilitate comparisons.�
The recorded video demonstration should focus on the interactive features of
the submission and the process of analyzing the data. We require a recorded
demonstration because interactivity is an important component and is difficult
to evaluate only through a paper submission.��
Demonstrations should try not exceed 10 minutes in length.� We recommend that you save your video as
Flash as most people will be able view them and they have a good compression
rate.�� If you are not familiar with
recorded video demonstrations take a look at Camtasia. It will work very
well for most systems (unless you have fast animation in which case you may
need to record with an external video recorder).� Include audio explanations.� Test your video by asking your friends if
they can read it (e.g. a common mistake is to not provide the video
codec).� Avoid .AVI or other format that
generates huge files.� If you anticipate
having difficulties generating a digital video, please contact the contest
chairs to arrange alternative submission methods.
The
2-page PDF summary should provide an overview of the tool and the analysis
process used, summarize the strengths and weaknesses of the approach, and
provide at least one example screen shot. The 2-page summary should be
formatted in two-column SIGGRAPH format as described the VAST 2006 Call for
Participation.�� The summaries of
accepted submissions will be published in the VAST adjunct proceedings and in
the IEEE Digital Library.� You will have
a chance to revise the summary early September, but the turnaround will be very
short.
How to submit?��� DEADLINE IS JULY
18th (midnight Pacific Standard Time)
We regret that we will be unable to accept ftp submissions
between 5:00 p.m. ET Friday, July 14 and 5:00 a.m. ET Monday, July 17.� If this should pose problems for you, please Email
the Contest Chairs.
To deliver your submissions:
1. Save all materials in a directory
with the answer form serving as an index.
2. Name
the directory to match the title of your submission: [Team � Name of tool].zip
(e.g. UMd-SuperVis.zip).
3. Zip
the entry materials into one or more files, limiting the size of each file to 1
GB. If you have more than one file add �-part1of2� etc. to the filename so we
can be sure we have all the files, e.g. UMd-SuperVis-part1of2.zip and
UMd-SuperVis-part2of2.zip
4. Use
Internet Explorer to go to ftp://ftp.nist.gov/pub/VAST/� and drag your files onto that directory
5. You
will not receive a confirmation from the site that your files have been
uploaded.
6. Send
an email to theresa.oconnell@nist.gov
to let us know that you have uploaded your files.
7. Within
two business days, we will confirm receipt of your submission or notify you of
any problems with your files. Thanks for submitting!
Related websites
Beliv'06: Upcoming workshop on evaluation of
information visualization at AVI'06
InfoVis Contest 2003,
2004, 2005
2007
TVCG paper summurizing InfoVis contest results and lessons learned.
Information
Visualization Benchmark Repository
IEEE VAST Conference
Questions?� �Email the Contest Chairs