Copy Link
Add to Bookmark
Report
VISION-LIST Digest 1990 11 30
Vision-List Digest Fri Nov 30 13:54:50 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Converting Rosenfeld's mebib troff format to BiBtex/Refer/etc.
Anyone doing PSYCHOPHYSICAL testing of image compression???
Graduate study in neural networks
7th IEEE Conference on AI Applications - Program available
Questionnaire on State of the Art in CAD-Based Vision Systems
----------------------------------------------------------------------
Date: Tue, 27 Nov 90 17:06:32 -0800
From: vision@deimos.ads.com (Philip Kahn)
Subject: converting Rosenfeld's mebib troff format to BiBtex/Refer/etc.
Rosenfeld's bibliographies are in a format called mebib. Several readers
have noted an interest in obtaining a database accessible version of his
references (e.g., in BibTex or Refer format). Please contact me if you
know how to do this or are interested in finding out how it can be done.
thanks,
phil...
------------------------------
Date: 28 Nov 90 05:38:03 GMT
From: David Honig <honig@ICS.UCI.EDU>
Subject: anyone doing PSYCHOPHYSICAL testing of image compression???
I'm interested in obtaining references to groups doing psychophysical
research on image and image-sequence compression methods. Where the
"psychophysical" study can be defined as anything more formal than
asking your neighbor, "hey Joe, how do ya' think this version looks?"
(which I'm afraid is all too common!)
Thanks,
David
------------------------------
Date: Fri, 30 Nov 90 15:13:20 -0500
From: caroly@park.bu.edu
Subject: graduate study in neural networks
GRADUATE PROGRAM IN COGNITIVE AND NEURAL SYSTEMS (CNS)
AT BOSTON UNIVERSITY
Gail A.Carpenter & Stephen Grossberg, Co-Directors
The Boston University graduate program in Cognitive and Neural Systems
offers comprehensive advanced training in the neural and computational
principles, mechanisms, and architectures that underly human and
animal behavior, and the application of neural network architectures
to the solution of outstanding technological problems.
Applications for Fall, 1991 admissions and financial aid are now
being accepted for both the MA and PhD degree programs.
To obtain a brochure describing the CNS Program and a set of application
materials, write or telephone:
Cognitive & Neural Systems Program
Boston University
111 Cummington Street, Room 240
Boston, MA 02215
(617) 353-9481
or send a mailing address to: caroly@park.bu.edu
Applications for admission and financial aid should be received by
the Graduate School Admissions Office no later than January 15.
Applicants are required to submit undergraduate (and, if applicable,
graduate) transcripts, three letters of recommendation, and Graduate
Record Examination (GRE) scores. The Advanced Test should be in the
candidate's area of departmental specialization. GRE scores may be
waived for MA candidates and, in exceptional cases, for PhD candidates,
but absence of these scores may decrease an applicant's chances for
admission and financial aid.
Description of the CNS Program:
The Cognitive and Neural Systems (CNS) Program provides advanced training
and research experience for graduate students interested in the neural and
computational principles, mechanisms, and architectures that underly human
and animal behavior, and the application of neural network architectures
to the solution of outstanding technological problems. Students are
trained in a broad range of areas concerning cognitive and neural systems,
including vision and image processing; speech and language understanding;
adaptive pattern recognition; associative learning and long-term memory;
cognitive information processing; self-organization; cooperative and
competitive network dynamics and short-term memory; reinforcement,
motivation, and attention; adaptive sensory-motor control and robotics;
and biological rhythms; as well as the mathematical and computational
methods needed to support advanced modeling research and applications. The
CNS Program awards MA, PhD, and BA/MA degrees.
The CNS Program embodies a number of unique features. Its core curriculum
consists of eight interdisciplinary graduate courses each of which
integrates the psychological, neurobiological, mathematical, and computational
information needed to theoretically investigate fundamental issues concerning
mind and brain processes and the applications of neural networks to technology.
Each course is taught once a week in the evening to make the program available
to qualified students, including working professionals, throughout the Boston
area. Students develop a coherent area of expertise by designing a program
that includes courses in areas such as Biology, Computer Science, Engineering,
Mathematics, and Psychology, in addition to courses in the CNS core curriculum.
The CNS Program prepares Ph.D. students for thesis research with scientists
in one of several Boston University research centers or groups, and with
Boston-area scientists collaborating with these centers. The unit most
closely linked to the Program is the Center for Adaptive Systems. The
Center for Adaptive Systems is also part of the Boston Consortium for
Behavioral and Neural Studies, a Boston-area multi-institutional
Congressional Center of Excellence. Another multi-institutional
Congressional Center of Excellence focussed at Boston University is the
Center for the Study of Rhythmic Processes. Other research resources
include distinguished research groups in dynamical systems within the
mathematics department; in theoretical computer science within the Computer
Science Department; in biophysics and computational physics within the
Physics Department; in sensory robotics, biomedical engineering, computer
and systems engineering, and neuromuscular research within the Engineering
School; and in neurophysiology, neuroanatomy, and neuropharmacology at the
Medical School.
------------------------------
Date: Wed, 28 Nov 90 10:50:28 EST
From: finin@PRC.Unisys.COM
Subject: 7th IEEE Conference on AI Applications - Program available
A copy of the advanced program of the the Seventh IEEE Conference on
Artificial Intelligence Applications (CAIA-91) is now available and can be
obtained by sending email to the mail agent CAIA-PROGRAM@PRC.UNISYS.COM. This
agent will respond to all messages by returning via email the text of the
advanced program, including a registration form and an accommodations form.
CAIA-91 will be held on February 24-28, 1991 at the Fontainbleau Hilton Resort
and Spa in Miami Beach, Florida. A series of twelve half-day tutorials will
be held on February 24th and 25th. The technical program will be held on
February 26th through the 28th. This will include 73 submitted papers, a
number panels and the following invited talks:
AI in Biology and Challenges of the Human Genome Project,
Bruce Buchanan, University of Pittsburgh
Technology and People, Eric Bloch, former director, NSF
Toward Intelligent Systems in the DoD, Major Steven Cross, DARPA
Application Projects at ICOT, K. C. Furukawa, ICOT
The ESPRIT Program, D. E. Talbot, Commission of the European Communities
"Applying Common Sense" - Necessity or Oxymoron?, Doug Lenat, MCC
For more information about the conference in general, or to request hardcopy
of the advanced program, contact: IEEE Computer Society, 1730 Massachusetts
Ave. NW, Washington, DC 20036, 202-371-1013, fax: 202-728-0884. For more
information about the technical program, contact: Tim Finin, Unisys Center for
Advanced Information Tech., PO Box 517, Paoli PA 19301, 215-648-2840, fax:
215-648-2288, finin@prc.unisys.com.
------------------------------
Date: Wed, 28 Nov 90 18:03:47 EST
From: Dr. Kevin Bowyer <kwb@midgit.csee.usf.edu>
Subject: Questionnaire on State of the Art in CAD-Based Vision Systems
IEEE Workshop on Directions in Automated ``CAD-Based'' Vision
June 2-3, 1991 Maui, Hawaii (just prior to CVPR '91)
Questionnaire on State of the Art in CAD-Based Vision Systems
This survey form is being distributed for the purpose of organizing
a panel session at the upcoming workshop on Directions in Automated
``CAD-Based'' Vision. We hope that this will serve to give the workshop
a sharper focus and to facilitate some interesting discussion. Responses
are solicited from all interested persons. Some representative subset
of the respondents will be asked to lead a panel discussion at the
workshop, organized by Avi Kak. A written report of the survey results
will also be prepared. Responses are needed by January 1. You may
respond by e-mail to kwb@sol.csee.usf.edu or by regular mail to
Kevin Bowyer / Department of Computer Science and Engineering /
University of South Florida / Tampa, Florida 33620 / USA.
1. What is the name of the system?
2. What is the system's purpose (intended application)?
3. What is the best generally accessible reference which describes the system?
4. What language(s) is the system written in?
5. What computer(s) does the system run on?
6. How long does it take to analyze the ``average'' scene of a single object?
(If multiple computers are listed just above, specify which one this time is for.)
7. How long does it take to analyze the ``average'' scene of a jumbled pile of about
a dozen objects in order to recognize at least one of the objects?
(If multiple computers are listed just above, specify which one this time is for.)
8. Is the computational complexity of the system known? If so, what is it?
(Specify order N-whatever, where N is ...)
9. What class of object shapes does the system handle?
10. Are object models entered into the system ...
by hand?
from a CAD system-- which one?
by a set of standard images?
some other method?
11. How many different objects are in the system database?
12. How many objects have been in the most complex scenes analyzed by the system?
Were these all the same object or different objects?
Have the objects all been made of the same material?
Have the objects all been the same color?
13. Does the system use ...
orthographic projection?
perspective projection?
orthographic with scale factor?
14. What type of imagery does the system use?
range-- if so, what type(s)?
intensity-- if so, grayscale or color?
other-- if so, what?
15. Does the system use a single view or multiple views?
16. If the system uses multiple views, are the viewpoints fixed ahead of time?
17. If the system uses multiple views from varying viewpoints, how are they selected?
18. Does the system incorporate a ``table-top'' assumption?
(That is, does it use explicit knowledge of a supporting plane for the objects?)
19. Can the system recognize occluded objects?
if they share a supporting plane (example-- one behind the other on a table)?
if they are laying on top of each other (example-- a pile of objects on a table)?
20. What type of image features are used by the system for matching?
purely shape-based (edges, contours, junctions)?
texture?
color?
other-- if so, what?
21. Does recognition include estimation of pose?
22. How many scenes has the system analyzed?
23. Is the lighting ...
``normal room lighting''?
special lighting set up some time ago and not changed between scene analyses?
optimized for each scene analysis?
under automatic control of the recognition system in some way?
24. Is the matching strategy based on:
interpretation trees of some type?
iterative optimization techniqes?
geometric hashing of some sort?
other-- if so, what?
25. What do you consider the strongest point of your system?
26. What do you consider the strongest point of CAD-based vision systems generally?
27. What do you consider the weakest point of your system?
28. What do you consider the weakest point of CAD-based vision systems generally?
29. What important dimension of CAD-based vision systems is not captured
in this survey?
30. E-mail and regular mail address for contacting you.
------------------------------
End of VISION-LIST
********************
