IEEE Workshop on Content-Based Access of Image and Video Libraries
in conjunction with CVPR '98
http://www.ctr.columbia.edu/cvpr98/workshop.html
June 21, 1998
Santa Barbara, California
----------------------------------------------------------------------------
General Chairs Call for Papers: The objective of this workshop is to
Chung-Sheng Li, promote information exchange and technical
IBM T.J. Watson interaction among researchers and developers working
Research Center on algorithms or systems for accessing visual content
in large image/video libraries.
Avi Kak,
Purdue Computer Vision and pattern recognition play an
University important role in solving many critical problems in
this area, in conjunction with other disciplines
Technical (e.g., image processing, database, and information
Program Chair retrieval). This workshop will focus on several
Shih-Fu Chang, important technical challenges, including
Columbia representation, analysis, indexing, retrieval,
University classification, and summarization of image/video
content.
Technical
Program Representation:
Committee
Albert Del Bimbo * Integrated models of various visual features
(Italy) * Image/video object representations
Ruud Bolle supporting content-based search
(IBM) * Description of spatio-temporal relationships
Carla Brodley of image/video objects
(Purdue U) * High-level event representations supporting
David Copper semantic queries
(Brown U)
Dave Forsyth
(UC Berkeley) Analysis:
Tom Huang
(UIUC) * Segmentation of image/video objects with
Ramesh Jain salient features/content
(UC San Diego) * Adaptive grouping of features and objects
S.Y. Kung * Compressed-domain feature extraction
(Princeton U) * Features linking across different levels
C. C. Jay Kuo
(USC) Indexing:
B.S. Manjunath
(UC Santa * Efficient indexing algorithms for
Barbara) high-dimensional feature space
Sanjit Mitra * Robust, scalable indexing algorithms for
(UC Santa spatio-temporal queries
Barbara)
A. Desai Retrieval:
Narasimhalu
(Singapore) * Efficient query interface for query
Wayne Niblack manipulation and relevance feedback
(IBM) * Integrated search in federated visual
Soo-Chang Pei information systems
(Taiwan) * User-friendly navigation through large
Remi Ronfard visual archives
(France) * Query optimization considering multiple
Ishwar Sethi criteria (e.g. storage, speed, bandwidth)
(Wayne State U.)
Linda Shapiro
(Wash. U) Classification:
Thomas Sikaro
(Germany) * Domain-specific or domain-independent
John R. Smith image/video classification
(IBM) * Automated (or semi-automated) generation of
Harold Stone image/video taxonomies
(NEC Research, * Semantic decoding and model selection
USA) through learning
Tanveer F.
Syeda-Mahmood Summarization:
(Xerox)
Murat Tekalp * Automated summarization of visual content
(U. Rochester) from single or multiple sources
Wayne Wolf * Visualization of visual content at different
(Princeton U) levels
Stephen Wong
(UC San
Francisco) Evaluation:
HongJiang Zhang
(HP Labs) * Metrics and benchmarking procedures for
performance evaluation
Original papers are solicited in, but not limited to,
the above technical areas.
Paper Submission: Four copies of the complete
manuscript should be sent by January 30, 1998 to:
Professor Shih-Fu Chang
Department of Electrical Engineering
Columbia University
New York, NY 10027
Tel: (212) 854-6894
Email:
sfchang@ctr.columbia.edu
Each paper should include a title page containing the
names and addresses of the authors (including e-mail
addresses), an abstract of up to 200 words, and at
least five subject keywords.
Each paper is limited to 10 double-spaced pages (or 5
single-spaced pages) including figures, references,
etc.
--------------------------------------------------------------------------
The dbworld list reaches many people, and should only be used for
messages of general interest to the database community.
To subscribe or unsubscribe yourself (or optionally (address)) from
dbworld, send a msg to majordomo@cs.wisc.edu with one of these lines:
subscribe dbworld (address)
unsubscribe dbworld (address)
To find out more options send a msg with the line:
help
--------------------------------------------------------------------------