www.Usenet.com
www.Usenet.com
| <-- __Chronological__ --> | <-- __Thread__ --> |
VISION-LIST Digest Fri Oct 17 11:31:37 PST 2003 Volume 22 : Issue 18
- ***** The Vision List host is VISLIST.COM *****
- Send submissions to [EMAIL PROTECTED]
- Vision List Digest and Archives available at http://WWW.VISLIST.COM
- If you don't have access to a web browser, you can read the
Vislist from the newsgroup comp.ai.vision or send email to
[EMAIL PROTECTED] to request mailing list membership
- Access Vision List Archives via anonymous ftp to ftp://FTP.VISLIST.COM
- Vision List supported by Directed Perception (http://www.DPerception.com)
Today's Topics:
Q&A : Release of Motion-2D software
Q&A : Comparing results with Mathematical Morphology programs
Q&A : MM-wave images
Q&A : Multiple camera Calibration
Q&A : Recommendation for image alignment and registration
Q&A : Technologies for occupant detection 'smart airbag'
JOB : Image Processing Scientist - STI - Hawaii
JOB : Application Developer - Lawrence Berkeley National Lab - CA
JOB : Image/Video Compression Scientist - UtopiaCompression -
JOB : Postdoc - SUNY - Syracuse, NY
JOB : Visiting Postdoc Fellow - Lawrence Berkeley National - CA
JOB : Studentship - Boston Univ - Boston, MA
CFP : Canadian Conf on Computer-Robot Vision - Ontario - Jan 26 2004
CFP : RIAO'2004 - France - Apr 26-28 2004
CFP : WS Processing Sensory Info - Oulu, Finland - Jan 31 2004
CFP : IEEE Data Mining'03 - Melbourne, FL - Nov 19-22 2003
----------------------------------------------------------------------
From: Bouthemy Patrick <[EMAIL PROTECTED]>
Subject: Q&A : Release of Motion-2D software
Organization: Irisa - Campus de Beaulieu - Rennes
The Vista research team (Irisa / Inria Rennes,
http://www.irisa.fr/vista) is pleased to
announce the release of Motion2D version 1.3.9.
Motion2D is a multi-platform object-oriented library to estimate 2D
parametric motion models in an image sequence. It can handle several
types of motion models, namely, constant (translation), affine, and
quadratic models. Moreover, it includes the possibility of accounting
for a global variation of illumination. The use of such motion models
has been proven adequate and efficient for a large range of issues, such
as optic flow computation, motion segmentation, detection of independent
moving objects, object tracking, or camera motion estimation, and in
numerous application domains, such as dynamic scene analysis, video
surveillance, visual servoing for robots, video coding, or video
indexing. Motion2D is based on a robust, multi-resolution and
incremental estimation method exploiting only the spatio-temporal
derivatives of the image intensity function (J.-M. Odobez and P.
Bouthemy, Robust multiresolution estimation of parametric motion models.
Journal of Visual Communication and Image Representation, 6(4):348-365,
December 1995).
Motion2D is released in different versions:
1. Motion2D Free Edition: version of Motion2D available for development
of Free and Open Source software only (no commercial use). It is
provided free of charge under the terms of the Q Public License found
in the LICENSE.QPL file. It includes the source code and makefiles
for Linux, Solaris, SunOS, and Irix.
2. Motion2D Professional Edition: version provided for commercial
software development. This version also supports Windows 95 and NT.
For questions regarding purchase and pricing (royalties) for the
Motion2D Professional Edition, please contact us at [EMAIL PROTECTED]
Motion2D Free Edition can be downloaded at
http://www.irisa.fr/vista/Motion2D
A fully cross-referenced online html documentation is available.
------------------------------
From: "Marcos I. Quintana" <[EMAIL PROTECTED]>
Subject: Q&A : Comparing results with Mathematical Morphology programs
I am a PhD student in the School of Computer Science, the University of
Birmingham, U.K. My field of study is evolutionary computation for image
analysis. This is concerned with automatically constructing computer
programs for image analysis, based on the examples of inputs and
outputs.
In the paper I presented at KBCS-2002 (cited below and available online)
we obtained some interesting results in the automatic programming of
mathematical morphology tasks for binary images.
Many of the results obtained seem to be as good as those that could be
obtained by an expert writing the algorithm by hand, but I do not have a
proof for this. I have written my own programs, but of course they may
not be as good as those written by better experts in mathematical
morphology. Ideally, for my PhD I would like to compare the output of
the automatic programs with the best hand-written algorithms.
I would like therefore to invite everyone to write some Mathematical
Morphology programs which extract simple features from binary images.
The rules are to use ONLY basic Mathematical Morphology operators (i.e.
erosion and dilation) and structuring elements of size 3X3, 5X5 and 7X7
(any shape). No other operations (arithmetic or logical) are permitted.
The task is to extract three features (heads, hooks and lines) from
music score sheets.
You may find all the necessary data files in:
http://www.cs.bham.ac.uk/~miq/examples/
The directory
http://www.cs.bham.ac.uk/~miq/examples/32
contains 32X32 images (PBM format). In sub-directory "fragments" there
are input images. In sub-directories "heads", "hooks" and "lines" there
are the corresponding (hand extracted) features: heads, hooks and lines
respectively. These are the desired outputs for the programs. There is
a similar directory for 64x64 images.
In the directory
http://www.cs.bham.ac.uk/~miq/examples/toccata/
you may find larger music score-sheets on which to test the programs you
may construct.
Please send me the programs and results you obtain for any images in
"toccata" directory.
I will acknowledge your contibutions in my thesis and any publications
that may come out of this project.
Probably the latest useful date for your solutions would be around
Christmas 2003.
If you think you could help, please email me in advance at:
mailto:[EMAIL PROTECTED]
Thank you!
Marcos
Paper:
M.I. Quintana, R. Poli and E. Claridge. Genetic Programming for
Mathematical Morphology Algorithm Design on Binary Images. In Sasikumar,
M. et.al., eds.: Artificial Intelligence, Proceedings of the International
Conference KBCS-2002, pp. 161-170, Mumbai, India, 19-21 Dec., Vikas 2003
Available at:
http://www.cs.bham.ac.uk/~miq/examples/KBCS2002.pdf
------------------------------
From: Zhu T <[EMAIL PROTECTED]>
Subject: Q&A : MM-wave images
I am looking for the registration of the visual and mm-wave images for
concealed weapon detaction. Please kindly provide me or recommend me
good sites.
------------------------------
From: "Jorge H. Usabiaga" <[EMAIL PROTECTED]>
Subject: Q&A : Multiple camera Calibration
I have to calibrate 3 or 6 cameras covering the volume of a big box. Do
you know any software that I could use.
Thank you in advance,
Jorge Usabiaga Phone: (775) 327-5087
Computer Vision Lab [EMAIL PROTECTED]
University of Nevada, Reno
------------------------------
From: [EMAIL PROTECTED] (Sam)
Subject: Q&A : Recommendation for image alignment and registration
Does anyone know of any good software package for image alignment and
registration? Also can anyone recommend a good 3D reconstruction package
for both CT or MRI data and images of physically cut serial sessions?
------------------------------
From: [EMAIL PROTECTED] (Rhita Boufelliga)
Subject: Q&A : Technologies for occupant detection 'smart airbag'
I am conducting research on different technologies for 3D measurements
that could be applicable in the automotive industry for airbag
deployment. Do you know of any resources, new technologies,
information...
Thank you, Rhita Boufelliga
------------------------------
From: "Holger Lange" <[EMAIL PROTECTED]>
Subject: JOB : Image Processing Scientist - STI - Hawaii
Image Processing Scientist - Ph.D. +2/4years experience - Science and
Technology (STI) - Hawaii
Seeking an image-processing scientist to work as part of the medical
image-processing group at Science and Technology International (STI),
Honolulu, Hawaii, on the development of a Computer Aided Diagnostic
(CAD) system for a new medical imaging modality. The new medical imaging
modality uses hyper-/multi- spectral imagery for the early detection of
cancer. The image processing scientist will provide his expertise in
classification (broad knowledge that should go beyond artificial neural
networks) and fusion (primarily for high level data like classification
results - broad knowledge that should include fuzzy logic and expert
system approaches) approaches to the CAD system development. The
image-processing scientist should be able to demonstrate good
programming skills in MATLAB and/or C/C++. The image-processing
scientist should have a Ph.D. with thesis work in image processing and
some (2-4 years) of industry experience.
Please contact: mailto:[EMAIL PROTECTED]
Holger Lange, Ph.D.
Science & Technology International (STI)
733 Bishop Street, Suite 3100, Honolulu, Hawaii 96813
Phone: (808) 540-4751, Fax: (808) 540-4850
------------------------------
From: Steve Deem <[EMAIL PROTECTED]>
Subject: JOB : Application Developer - Lawrence Berkeley National Lab - CA
Lawrence Berkeley National Lab
Berkeley Lab is a multidisciplinary scientific and high-performance
computing facility conducting non-classified research. We are looking
for an Applications Developer who has a background in image analysis,
user interfaces, and C++ programming.
The right person will develop and implement imaging and informatics
system for scientific applications.
Responsibilities also include developing and implementing computational
techniques for feature-based representation of scientific images and
data. Develop open-source software to interact with standardized data
exchange format. Interact with the science team on a routine basis and
to publish research results in leading conferences and journals.
Requires a B.S. or M.S. in Computer Science or Electrical Engineering
with strong emphasis on image analysis, user interface design, and
database integration or equivalent experience. The applicant must be
well-versed in statistical techniques for data analysis and the use of
Bayesian models for knowledge representation. Applicant is required to
have a strong analytical background and have a deep knowledge object
oriented design techniques to produce production quality software in
C++. This person will develop, implement, and apply computational vision
algorithms for analysis of scientific imaging data.
To apply for this position, submit a resume with a cover letter and Job#
016422 by email to [EMAIL PROTECTED] (no attachments please); by fax
to (510) 486-5870; or by mail to Berkeley Lab Staffing Office, One
Cyclotron Road, MS 937-0600, Berkeley, CA 94720. AA/EOE.
------------------------------
From: "Juhn Maing" <[EMAIL PROTECTED]>
Subject: JOB : Image/Video Compression Scientist - UtopiaCompression -
POSITION: IMAGE/VIDEO COMPRESSION SCIENTIST
Job Description
UtopiaCompression is looking for a highly qualified candidate with
extensive experience and knowledge in image, especially video
compression. The candidate is required to have an MS or Ph.D. from a
highly reputable university. Post-doctorate and/or industry experience
is strongly preferred. The ideal candidate will be thoroughly versed in
the latest research, methods, developments and theories in image and
video compression and processing as well as possess in-depth experience
applying them to commercial, scientific or industrial applications. The
candidate is also required to be a great problem solver capable of
proposing solutions to multiple problems in parallel, and mentoring and
guiding R&D engineers in developing and implementing the solutions.
Permanent residents or US citizens are preferred.
This position is ideally suited for full-time employment, but part-time,
contract and contract-to-hire arrangements may also be considered.
Skills & Qualifications
1 - In-depth knowledge and experience in various compression methods:
lossy and lossless compressions, Huffman, arithmetic, differential,
runlength, transformation (e.g., DCT, Wavelet), vector quantization,
fractal based coding, etc.
2 - In-depth knowledge and experience in image compression standards and
specifications, their advantages and disadvantages, their
limitations in various imaging markets and their relationships to
other technology advancements and components in building whole
solutions. Close familiarity with different codec systems.
3 - In-depth knowledge and experience in various signal and image
processing techniques such as sampling and quantization,
transformations techniques and frequency analysis, smoothening,
enhancement, edge detection, feature analysis, restoration,
segmentation, coloring, filtering, etc.
4 - In-depth knowledge and experience in computational vision, in
particular psychovision, and volumetric imaging.
5 - Fluency in software analysis, design and development using C
programming environment. Candidates must be well versed and
experienced in C. Working experience in C++ (and Java) a plus.
6 - Dexterous familiarity with software tools such as MatLab, Adobe
PhotoShop, etc.
7 - Knowledge and experience in packaging codecs into
software/hardware/hybrid solutions appropriates for vertical
applications in Media & Entertainment, Wireless, Surveillance &
Security, Medical Imaging, etc., is a plus.
8 - Knowledge and working experience in artificial intelligence, machine
learning, statistical analysis and reasoning is preferable, as well
as working experience in neural nets, (numeric) decision tree
learning, genetic programming, fuzzy reasoning, searching and
inferencing, (statistical) optimization algorithms, etc.
Send resume to:
Juhn Maing, UtopiaCompression
Tel: 310-473-1500 x104 / Fax 310-473-5052
mailto:[EMAIL PROTECTED]
------------------------------
From: Dan Tso <[EMAIL PROTECTED]>
Subject: JOB : Postdoc - SUNY - Syracuse, NY
Title of Position: Postdoctoral Associate in Visual Neurophysiology
Date position is available: immediately
Requirements: (some of the following) experience in CNS electrophysiology,
visual psychophysics, awake behaving primate preparations, computer
programming, fMRI techniques.
Field of work and duties:
Participation in a research program studying information processing,
connectivity, functional organization, and neuronal dynamics in the
visual cortex, involving single unit electrophysiology, anatomical
tracing, awake behaving primates and optical imaging. Research topics
include color vision, neuronal connectivity and relationships between
physiology and psychophysics.
Principal Investigator: Daniel Ts'o
SUNY
Syracuse, NY
(315)-464-5531
[EMAIL PROTECTED]
------------------------------
From: Steve Deem <[EMAIL PROTECTED]>
Subject: JOB : Visiting Postdoc Fellow - Lawrence Berkeley National - CA
Lawrence Berkeley National Lab
Berkeley Lab is a multidisciplinary scientific and high-performance
computing facility conducting non-classified research. We are looking
for a Computer Vision Visiting Postdoc Fellow who has a background in
algorithm development for scientific images, object oriented design, and
C++ programming.
This person will develop, implement, and apply computational vision
algorithms for analysis of scientific imaging data.
They will also develop and implement advanced computational techniques
for analysis of scientific images and to construct 2D and 3D models from
observational data. Develop a suitable representation from
multidimensional image space and to use this representation in
subsequent data mining. The successful candidate will be required to
work closely with the application scientists and to publish their work
in leading journals and conferences.
Requirements include a Ph.D. in Computer Science or Electrical
Engineering with emphasis on computer vision and image databases with a
strong analytical and implementation capability. Applicant must have a
significant publication record in the area of computer vision, pattern
recognition, and learning techniques. Applicant is required to have a
deep knowledge of object oriented design techniques to produce
production quality software in C++.
To apply for this position, submit a resume with a cover letter and Job#
016421 by email to [EMAIL PROTECTED] (no attachments please); by fax
to (510) 486-5870; or by mail to Berkeley Lab Staffing Office, One
Cyclotron Road, MS 937-0600, Berkeley, CA 94720. AA/EOE.
------------------------------
From: CNS Department <[EMAIL PROTECTED]>
Subject: JOB : Studentship - Boston Univ - Boston, MA
GRADUATE TRAINING IN THE
DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS (CNS)
AT BOSTON UNIVERSITY
The Boston University Department of Cognitive and Neural Systems offers
comprehensive graduate training in the neural and computational
principles, mechanisms, and architectures that underlie human and animal
behavior, and the application of neural network architectures to the
solution of technological problems.
The brochure may also be viewed on line at:
http://www.cns.bu.edu/brochure/ and application forms at:
http://www.bu.edu/cas/graduate/application.html
Applications for Fall 2004 admission and financial aid are now being
accepted for PhD, MA, and BA/MA degree programs.
To obtain a brochure describing CNS programs and a set of application
materials, write, telephone, or fax:
DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS
Boston University, 677 Beacon Street, Boston, MA 02215
617/353-9481 (phone), 617/353-7755 (fax)
or send via email your full name and mailing address to the attention of
Mr. Robin Amos at: mailto:[EMAIL PROTECTED]
Applications for admission and financial aid should be received by the
Graduate School Admissions Office no later than January 15. Late
applications will be considered until May 1; after that date
applications will be considered only as special cases.
Applicants are required to submit undergraduate (and, if applicable,
graduate) transcripts, three letters of recommendation, and Graduate
Record Examination (GRE) general test scores. GRE scores may be waived
for MA candidates and, in exceptional cases, for PhD candidates, but
absence of these scores will decrease an applicant's chances for
admission and financial aid.
Non-degree students may also enroll in CNS courses on a part-time basis.
*******************************************************************
Description of the CNS Department:
[ Omitted for brevity. Please visit their website if interested.
phil... ]
------------------------------
From: "John S. Zelek" <[EMAIL PROTECTED]>
Subject: CFP : Canadian Conf on Computer-Robot Vision - Ontario - Jan 26 2004
Organization: University of Guelph
Vision Interface has been renamed to
Canadian Conference on Computer and Robot Vision (CRV2004)
The 17th Vision Interface conference now becomes the 1st Canadian
Conference on Computer and Robot Vision. CRV will be held jointly
with AI 2004 and GI 2004, May 17-19 at the University of Western
Ontario in London, Ontario, Canada.
Download a printable pdf http://www.cipprs.org/CRV/crv2004.pdf of
this page.
Our sponsors are the Canadian Image Processing and Pattern
Recognition Society http://www.cipprs.org (CIPPRS) and the
International Association of Pattern Recognition
http://www.iapr.org . We are also hoping to hold our conference
in cooperation with the IEEE Computer Society
http://www.computer.org , who may publish our proceedings in
paper format and on-line.
The Canadian Conference on Computer and Robot Vision (CRV2004) is
a single-track conference consisting of high quality, previously
unpublished papers, presented either orally or as a poster.
Contributions are sought on any aspect of computer vision, robot
vision, image processing or pattern recognition, including but not
restricted to the following topics:
* 2D/3D Scene analysis
* Active Vision
* Applications - biomedical, robotic, surveillance,
inspection, entertainment
* Augmented Reality
* Biometrics
* Biological & Psychological aspects of Vision
* Calibration & Rectification (Mosaicing)
* Document Processing & Handwriting Recognition (OCR)
* Early Vision
* Face Detection & Recognition
* Gesture Detection & Recognition
* Graphics Recognition/Engineering Drawings
* Human Activity Recognition
* Human-Computer Interaction
* Image/Video Databases (multi-media, image/video retrieval)
* Image Segmentation & Classification
* Industrial applications (manufacturing)
* Learning & Classification methods
* Motion Analysis (optical flow, structure from motion,
correspondences)
* Neural Nets for Vision & Image Understanding
* Object Recognition
* Performance Evaluation Techniques
* Real-time Vision
* Robotic Vision (general)
* Servo-control
* Vision based navigation
* Environment modelling
* Sensor fusion
* Sensor Reliability
* Robot Mapping/Localisation
* SLAM (Simultaneous Localization and Mapping)
* Robot Control Architectures
* Real-time sensing and control
* Reactive systems
* Sensor-based control
* Shared control
* Augmented reality
* Learning from sensor data
* Shape Analysis
* Stereo vision
* Texture Analysis
* Tracking (2D/3D)
* Video Processing (motion, segmentation, registration)
* Medical Image Analysis
The conference provides an excellent environment for
interdisciplinary interaction as well as for networking of
students and scientists in computer vision, robotic vision, image
understanding and pattern recognition. In addition to regular
sessions, there will be also 3 invited speakers. There will be 2
awards: one for the best regular paper and one for the best
student paper (the student must be the first author).
REGISTRATION:
For a single registration fee, participants can attend
presentations in any of the AI/GI/CRV conferences. This conference
promotes participation of students by significantly reducing the
student registration fee. There is also a reduction in
registration fees for CIPPRS members and IEEE members (if we are
successful in obtaining co-sponsorship/cooperation). CIPPRS
welcomes members from all countries. You can obtain a registration
form at the CIPPRS website http://www.cipprs.org .
* JOINT CONFERENCES:*
CRV2004 will be held in conjunction with GI'2004 (Graphics
Interface) and AI'2004 (Artificial Intelligence). For a single
registration fee, participants can attend presentations at any of
AI/GI/CRV conferences. Fees to attend all three conferences are
the same. Proceedings of the other conferences can be purchased at
the conference.
*PAPER SUBMISSIONS:*
Papers are invited in either French or English. Submissions in
French should be accompanied by an abstract in English. The size
of the papers should be limited to eight double-column pages.
Style files for latex and Word are available at the CIPPRS website
http://www.cipprs.org . Submissions (in pdf only) are to be done
electronically through a conference website (not available yet).
In addition, the abstract and contact information should be
emailed to John Barron, program co-chair at [EMAIL PROTECTED]
All papers will be thoroughly reviewed by the Program Committee.
The accepted papers will be published in the conference
proceedings, the hardcopy of which will be distributed at the
conference. The proceedings will also be made available on-line by
either IEEE or CIPPRS websites. The best papers will also be
solicited for a special volume of a journal (to be announced).
*INVITED SPEAKERS (2004):*
1. Greg Dudek, McGill University, Montreal
2. Hong Zhong, University of Alberta, Edmonton
3. John Tsotsos, York University, Toronto
*IMPORTANT DATES:*
Paper Submission Deadline: January 26th, 2004
Acceptance/Rejection notification: March 3rd, 2004
Revised camera-ready papers due: April 2nd, 2004
Proceedings put online: May 28th, 2004
Chair1 Chair2
John Barron John S. Zelek
Dept. of Computer Science Robot Vision Group (ISL)
Middlesex College 379 School of Engineering
University of Western Ontario University of Guelph
London, ON, Canada, N6A 5B7 Guelph, ON, Canada N1G 2W1
[EMAIL PROTECTED] [EMAIL PROTECTED]
Tel:(519) 661-2111 x86896 Tel: (519) 849-4120 x3916
Fax:(519) 661-3515 Fax: (519) 836-0227
PROGRAM COMMITTEE:
Member Institution Country
Samer Abdallah American U. of Beirut Lebanon
Rob Allison York Univ. Canada
Steven Beauchemin U. of Western Ontario Canada
Gregory Dudek McGill U. Canada
Abdel Ennaji U. de Rouen France
Dmitry Gorodnichy National Research Council Canada
Robert Bergevin Laval U. Canada
Gerhard Roth National Research Council Canada
Michael Greenspan Queens U. Canada
Andrzej Kasinski Poznan U. of Tech. Poland
Reinhard Klette Auckland U. New Zealand
Michael Langer McGill U. Canada
Jim Little U. of British Columbia Canada
Jean Meunier U. de Montreal Canada
Evangelos Milos Dalhousie U. Canada
Fathallah Nouboud U. de Quebec a TR Canada
Pierre Payeur U. of Ottawa Canada
Georges Stamon U. of Paris France
Hagen Spies Linkoping U. Sweden
Matthew Turk U. of Cal. at Santa Barbara USA
Kazuhiko Yamamoto Gifu U. Japan
Hezy Yeshurun Tel-Aviv U. Israel
Hong Zhang U. of Alberta Canada
Michael Jenkin York U. Canada
Pierre Boulanger U. of Alberta Canada
Paul Whelan Dublin City U. Ireland
Minas Spetsakis York U. Canada
Denis Laurendeau Laval U. Canada
Djemel Ziou U. de Scherbrooke Canada
Denis Laurendeau Laval U. Canada
Terry Caelli U. of Alberta Canada
Medhat Moussan U. of Guelph Canada
Bubaker Boufama U. of Windsor Canada
Steven Beauchemin U. of Western Ontario Canada
*Venue:* London is Ontario's 3rd largest city (340,000). It has
the ambiance of a small town and the amenities of a large city.
Its nick name is "Forest City" because of the many tree lined
streets. Founded in 1820, it is ideally situated, about 200km from
Toronto, 250km from Detroit and 150Km from Niagara Falls. It has
many local attractions, including Pioneer Village (see how early
settlers lived and worked), Sha-Nah-Doht Iroquoian Village and
Museum (see how Indians lived in the London area before European
settlement) and Elgin House (the pre-Victorian home of an early
prominent London family). The conference will be held at the
University of Western Ontario. Attendees may stay at one of the
nearby hotels or in campus residence.
Some scenes of London, Ontario (move your cursor over the images to get
more information)
London Skyline from the North Middlesex College at the University of
Western Ontario (Computer Science Department)
A bend on the Thames River Riding an antique bike in Pioneer Village
Hope to see you in London, Ontario!
This page last updated on September 12, 2004
http://www.cipprs.org/CRV/
------------------------------
From: Benoit Mathieu 205535 <[EMAIL PROTECTED]>
Subject: CFP : RIAO'2004 - France - Apr 26-28 2004
Call For Papers and Applications
RIAO'2004
Coupling Approaches, Coupling Media and Coupling Languages for
Information Retrieval
University of Avignon (Vaucluse), France
April 26th-28th, 2004
Organized by:
CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE
(C.I.D., France)
in cooperation with the LIA (Laboratoire d'Informatique d'Avignon -
Université d'Avignon)
and with technical support of IRIT (Institut de Recherche en
Informatique de Toulouse)
CALL FOR PAPERS
Current content-based information management involves many different
disciplines. Information must be retrieved from video, from sound, and
from images and graphs. Question answering involves both syntax and
semantics.
Information classification and filtering involve machine learning and
linguistics. In addition, as information technology spreads throughout
the world, a wider variety of languages in increasingly complex
combinations must be handled.
In response to these evolving needs, RIAO'2004 calls for papers covering
the coupling of techniques from different domains to improve information
retrieval. RIAO'2004 will present innovative research and developments
from all areas of multi-media and multi-language information retrieval.
Submissions, demonstrating combination of techniques from disparate
domains, may treat retrieval from either a single medium, or across
media (indexing one medium for find information in another), or from
coupling unstructured and structured information (e.g. exploiting both
text and XML structure), or from across languages.
Conference Themes:
Paper submissions should cover one or more of the following themes:
Multimedia information:
* Media-specific indexing techniques (text, speech, fixed and
animated images, music)
* Indexing composite documents
* Querying multimedia documents
* Automatically generating text from images and from video
* Indexing interactive documents
Multilingual Information:
* Cross-lingual information retrieval, especially involving
rarer languages
* Automatic construction of bilingual lexicons and term banks
* Production of multilingual documents
Man Machine Combinations:
* Coupling search and browsing
* Coupling search and semantic mapping (ontologies, SOM, etc)
* Multimodal interfaces
* Coupling access through structure and through content
* Automatic presentation of search aids (e.g. key words, phrases)
* Neuroscience applied to information recognition
Architecture for Combined Approaches:
* Architecture for coupling techniques (e.g. Machine Learning for
Content Management)
* Architecture for coupling media
* Architecture for treating multilingual information
Specific Systems Combining Diverse Approaches:
* Systems for Collaborative Information Retrieval
* Question answering systems
* Multidocument or multilingual summarization
* Automatic translation, translation memory
Combining Linguistic and Statistics for Retrieving Content:
* Improved linguistic analyzers in information retrieval
* Exploiting linguistic knowledge in search and retrieval
* Knowledge Extraction for Information Retrieval
* Semantics in indexation and retrieval
Composite Documents and Content:
* Exploiting document structure
* Semantic Web, and Ontologies for Full-Scale Information Retrieval
* Exploiting new multimedia norms for content-based information
management
Evaluation of Combined Approaches:
* User oriented retrieval metrics
* New retrieval metrics
* Question-Answering systems evaluation metrics
Application domains combining techniques:
(descriptions of systems involving the following domains):
* Cultural heritage
* Indexation and retrieval of medical images
* Applications concerning security
* Protection of intellectual property
* Protection of minors
* E-learning
* Technology Watch
Important dates:
First call for papers: October 1, 2003
Deadline for paper submission: December 15, 2003
Notification of acceptance of papers: January 31, 2004
Camera-ready copies due: March 8, 2004
Conference dates: April 26-28, 2004
Submissions should be about 6000 words (about 20 pages, double spaced),
include and abstract and be submitted in PDF or PS format.
Submissions for communications will be made electronically on its web
site : http://www.riao.org .
The working language of the conference is English. However, in
agreement with the French regulations of the "Loi Toubon", submission of
papers in French and presentation of papers, if selected, in French will
be accepted.
CALL FOR APPLICATIONS
Innovative applications and products related to the conference topics
are sought for demonstrations during the three days of the Conference.
They will be selected by the international Application committee, on the
basis of their innovation and future or present marketability. Selected
applications will be given free demonstrations spaces.
Application submissions should cover one or more of the following
topics:
* Multimedia indexing and retrieval systems (text, sound,
speech, images, video)
* Cross-lingual indexing and retrieval systems
* Peer-to-peer text search engines
* Cooperative Information Retrieval (grids)
* Automatic XML structuring of documents
* Automatic metadata generation for text, sound, and
images, automatic annotators
* Automated ontology construction and annotators
* Topic detection and event detection in streaming
documents, technology watch, strategy watch
* Intelligent message filtering
* Intelligent text agents
* Parent control and anti-spam control by content filtering
* E-learning - response interpretation
* Document summarisation -- mono or multilingal, mono
or multidocument, profile driven
* Topic maps
* Domain-specific application of information retrieval
and multimedia retrieval: medicine, e-commerce,
computer-assisted teaching, video production, etc
Important dates:
First call for applications: October 1, 2003
Deadline for application submission: January 31, 2004
Notification for acceptance of applications: March 15, 2004
Conference dates: April 26-28, 2004
Program Committee
Co-Chairs Christian Fluhr Gregory Grefenstette Bruce Croft
CEA, France Clairvoyance UMass, Amherst,USA
Europe, Africa Asia, Oceania Americas
Catherine Berrut IMAG, France
Francine Chen PARC, USA
Claude Chrisment IRIT, Toulouse, France
Franciska de Jong Univ. Twente, Netherland
Claude de Loupy Sinequa, France
Renato De Mori Univ. Avignon, France
Marc El-Bèze Univ. Avignon, France
Pascale Fung Scienc. Tech. Univ., Hong Kong
Sadaoki Furui Tokyo Inst. Tech., Japan
Jean-Luc Gauvain LIMSI, France
Edouard Geoffrois ETCA/DGA, France
Julio Gonzalo UNED, Spain
Donna Harman NIST, USA
Ulrich Heid Univ. Stuttgart, Germany
Eduard Hovy ISI, Univ. S. California, USA
Christian Jacquemin LIMSI, France
Boris Katz MIT, USA
Elisabeth Liddy Univ. Syracuse, USA
Simone Marinai Univ. Florence, Italy
José Martinez Univ. Nantes, France
Christof Monz Univ. Amsterdam, Netherland
Frank Nack CWI, Netherland
Chahab Nastar LTU, France
Jian-Yun Nie Univ. Montréal, Canada
Douglas Oard Univ. Maryland, USA
Jörg Ontrup Univ. Bielefeld, Germany
Gabriella Pasi Univ. Milano, Italy
Marie Theresa Pazienza Univ. Roma, Italy
Marc Pic Advestigo, France
Jean-Marie Pierrel INALF, France
Jean-Marie Pinon INSA Lyon, France
Yan Qu Clairvoyance, USA
Steve Renals Univ. Sheffield, Great Britain
Tetsuya Sakai Toshiba, Japan
Frédérique Segond Xerox, France
Bernadette Sharp Staffordshire, Great Britain
Alan Smeaton Univ. Dublin, Ireland
Tokunaga Takenobu Tokyo Inst. Tech., Japan
Simone Teufel Univ. Cambridge, Great Britain
Evelyne Tzoukermann ACM, USA
Keith Van Rijsbergen Univ. Glasgow, Great Britain
Ross Wilkinson CSIRO, Australia
Zhiping Zheng Univ. Saarland, Germany
(Final list forthcoming)
Applications Committee
Chair Chantal Soulé-Dupuy
Université de Toulouse, France
(Forming Committee)
Organisation and Coordination Committee
Chair Agnès Beriot
Déléguée Générale du C.I.D., France
Peter Brodnitz Ogilvy & Mather, Japan
Jean Louis d'Arc Fédération France-Polonge, France
Jean Perrière Administrator, Secretary General,
C.I.D.,
France
Saryn Rosart CASIS, USA
Anne Tabutiaux Recherche et Diffusion, France
(Final list forthcoming)
Local Organisation Committee
Aurélia Barrière Univ. Avignon, France
Stéphane Igounet Univ. Avignon, France
(Final list forthcoming)
Technical Committee
President Luc Boulianne
C.I.D., Canada
Jonathan Albert C.I.D., Canada
Max Chevalier Univ. Toulouse, France
Jean-Jacques Guilbart Collège de France, France
Cécile Laffaire Univ. Toulouse, France
(Final list forthcoming)
Contact Information
Centre de Hautes Etudes Internationales d'Informatique Documentaire
(C.I.D.)
36 bis rue Ballu, 75009 Paris France
Tel: (33 / 0) 1 42 85 04 75, Fax: (33 / 0) 1 48 78 49 61
Email: [EMAIL PROTECTED]
Web: http://www.le-cid.org
------------------------------
From: Janne Heikkila <[EMAIL PROTECTED]>
Subject: CFP : WS Processing Sensory Info - Oulu, Finland - Jan 31 2004
PSIPS 2004 Call for Papers
An international workshop on Processing Sensory Information for
Proactive Systems (PSIPS 2004) will be arranged in
Oulu, Finland, on June 14-15, 2004, see http://www.psips2004.oulu.fi/.
Oulu is a well-known high-technology city in North Finland,
situated not far from the Arctic Circle. This is the fifth in the series
of machine vision and media processing workshops supported by Infotech
Oulu. The workshop is also supported by the Finnish Artificial
Intelligence Society and Pattern Recognition Society of Finland.
Proactive computing is a new area of research, in which the goal is to
develop systems that can adapt and adjust to the user's
movements and actions without requiring any conscious control. It can
be seen as the next significant step in development
from the current phase of user-oriented information technology, which
is based on interaction between man and machine. A three-year research
program on proactive computing was recently begun
in Finland, financed by the Academy of Finland.
The aim of this workshop is to provide a forum for presenting recent
research results and for discussing how to support
application development. The program of the workshop includes plenary
presentations by leading experts and contributed papers describing
recent progress in this field. The papers presented in the workshop will
be published in the workshop proceedings.
Workshop topics:
This workshop focuses on methods, sensors, and networks to view and
interpret the scene and human activities in proactive
systems. Contributions are expected from, but not limited to the
following areas:
- context recognition
- human detection and recognition
- analysis of events and human actions
- sensory signal analysis
- computer vision
- sensor solutions
- system architectures
Important dates:
Deadline for extended summary (>1000 words): January 31, 2004
Notification of acceptance: March 10, 2004
Deadline for camera-ready copy: May 15, 2004
Deadline for early registration: May 15, 2004
Keynote speakers:
Prof. James L. Crowley, Institut National Polytechnique de Grenoble,
France
Others to be confirmed
Paper submission:
Extended summary (>1000 words) should be submitted electronically via
the workhop web site (http://www.psips2004.oulu.fi/).
Financial support:
Some financial support for the foreign participants presenting a paper
in the workshop is available on request. A free form application should
be addressed to Minna Rautio ([EMAIL PROTECTED]
<mailto:[EMAIL PROTECTED]>) by March 31,
2004.
Organization:
Workshop chair: Prof. Matti Pietikainen ( mailto:[EMAIL PROTECTED] )
Program chair: Prof. Olli Silven ( mailto:[EMAIL PROTECTED] )
Local organization chair: Prof. Janne Heikkila ( mailto:[EMAIL PROTECTED] )
Secretariat: Ms. Minna Rautio ( mailto:[EMAIL PROTECTED] )
------------------------------
From: [EMAIL PROTECTED]
Subject: CFP : IEEE Data Mining'03 - Melbourne, FL - Nov 19-22 2003
IEEE Data Mining 2003: Call for Participation
The 2003 IEEE International Conference on Data Mining (ICDM)
to be held at the Holiday Inn Oceanfront, Melbourne, Florida, USA
November 19 - 22, 2003, invites you to attend.
* On-line registration (and other information) is available at
http://www.cs.uvm.edu/~xwu/icdm-03.html
Register by October 17 to get the early-bird rate!
* Registration includes a half-day tour of the NASA Kennedy Space Center!
* Be sure to book hotel rooms by October 31 at 5pm for discounted rates
(http://www.cs.uvm.edu/~xwu/icdm/hotel-03.shtml)
ICDM received a total of 501 paper submissions this year, from which
58 regular papers, 61 short papers, and 9 industry-track papers were
selected for presentation.
Conference highlights include the following.
* Five Invited Speakers:
- Thomas G. Dietterich, Oregon State University, USA.
"Sequential Supervised Learning:
General Methods for Sequence Labeling and Segmentation"
- Usama M. Fayyad, DMX Group, LLC, USA.
"Grand Challenges on the Road to Practical Data Mining Systems"
- Heikki Mannila, University of Helsinki, Finland.
"Global Structure from Sequences"
- Gene W. Myers, University of California, Berkeley, USA.
"Pattern Discovery for Genomics"
- Philip S. Yu, IBM T.J. Watson Research Center, USA.
"Real-Time Monitoring and Surveillance using Data Stream Mining"
* Four Tutorials:
November 19, Morning
- Chris Ding, "Bioinformatics and Machine Learning Methods"
- Ronen Feldman, "Information Extraction: Theory and Practice"
November 19, Afternoon
- Alexander Hinneburg and Daniel Keim,
"Advances in Clustering and Applications"
- Aleksandar Lazarevic, Jaideep Srivastava, and Vipin Kumar,
"Data Mining for Security Applications"
* Six Full-Day Workshops (November 19):
- Clustering Large Data Sets
- Data Mining for Computer Security (DMSEC '03)
- Foundations and New Directions in Data Mining
- Frequent Itemset Mining Implementations (FIMI '03)
- Privacy Preserving Data Mining (PPDM)
- [EMAIL PROTECTED]: The 3rd International Workshop on Visual Data Mining
* One Panel:
"Security and Data Mining: Funding Priorities and Opportunities"
Panel Chair: Michael J. Pazzani, National Science Foundation, USA.
* 128 Technical Paper Presentations (November 20 - 22, 2003):
There are sessions on Association Analysis, Bayesian Networks,
Clustering, Databases and Datamining, Feature Selection,
Mining Sequential and Hierarchical Data, Mining User Behavior,
Spatial and Temporal Tasks, Support Vector Machines,
Nearest-Neighbor Methods, Privacy-Preserving Datamining,
Linkage-based Methods, Rule-Based Methods, Text Mining,
Visualization, Image Processing, Issues in Supervised Learning, and
Applications.
------------------------------
End of VISION-LIST digest 22.18
************************
| <-- __Chronological__ --> | <-- __Thread__ --> |
