HOME    »    PROGRAMS/ACTIVITIES    »    Annual Thematic Program
IMA Workshop 6B
Digital Libraries: Classification, Retrieval and Visualization
February 26 - March 2, 2001


with partial support by The Office of Naval Research

Organizers:

David Forsyth
EECS
University of California-Berkeley
daf@cs.berkeley.edu

B.S. Manjunath
Department of Electrical and Computer Engineering
University of California-Santa Barbara
manj@ece.ucsb.edu

Francois Pachet
SONY CSL-Paris
pachet@csl.sony.fr

A large collection is valuable only if users can find what they want, when they want it. The key issue is describing and recognising media content in a fashion that is consistent with user needs. As a result, a negotiation between user needs and technological capacity is inevitable, and a good knowledge of likely user requirements can make the difference between success and failure.

Users are often interested in semantic categorisation, which is seldom available; the trick is to construct recognition processes that usefully mimic semantic categories. Recognition is poorly understood, but the most useful mathematical ideas appear to be statistical in nature, including classification, statistical learning theory, and probabilistic inference; often "natural" recognition strategies (such as Bayesian inference) are computationally infeasible, and there is a dearth of results that link statistical accuracy with computational cost in useful ways.

Search is made easier by summarizing content. This trick works at a variety of levels: for a collection, one might use a very small subset of images (or videos, or audio tracks, or...) to indicate both the type of content and the rough distribution of types; similarly, representing a video by a few well chosen frames can make interactive browsing fast and efficient. Summarization draws mainly on transform and coding theory.

Current search tools are weak. Browsing tools can make weak search tools very useful, by making it easier to navigate from the response of a search tool to the right place in a collection. Good browsing tools are fast and responsive, and use the display to guide the user to an understanding of the local structure of the collection. Isometric embeddings of graphs and Haar measure are mathematical tools that have proven useful here.

The workshop will:

  • acquaint researchers with the state of the art of knowledge in user needs and the technology available to meet these needs

  • drive theoretical research in areas such as learning, classification and inference by describing the technology needs of system builders

  • build collaborations between researchers with appropriate theoretical backgrounds and system builders.

Appropriate attendees are: mathematicians and statisticians interested in classification, learning and inference, in transforms or coding theory or in applications of geometry; multimedia practitioners interested in retrieval of various forms of content, including documents, images, video and music; and multimedia practitioners interested in managing, browsing or visualising large collections of data.

WORKSHOP SCHEDULE

Monday Tuesday
MONDAY, FEBRUARY 26
All talks are in Lind Hall 409 unless otherwise noted.
8:30 am Coffee and Registration

Lind Hall 400

9:10 am Willard Miller, Fred Dulles Welcome and Introduction
9:30 am David Forsyth
University of California - Berkeley
Clustering, Object Recognition and Picture Retrieval
10:30 am Break Lind Hall 400
11:00 am-12:00 pm B.S. Manjunath
University of California-Santa Barbara
Image Retrieval: An Overview
2:00 pm Francois Pachet
SONY CSL-Paris

Music Content Management for Electronic Music Distribution What is "Interesting Music"?

Slides    pdf    html

3:00 pm Break Lind Hall 400
3:30-4:30 pm Peter Pirolli
Xerox PARC

Information Foraging and Information Scent: Theory, Models, and Applications

Slides   pdf    html

4:30 pm IMA Tea
A variety of appetizers and beverages will be served.
Lind Hall 400
TUESDAY, FEBRUARY 27
All talks are in Lind Hall 409 unless otherwise noted.
9:15 am Coffee Lind Hall 400
9:30 am

P. Anandan
Microsoft Research

Layered Representations of Visual Scene Information in Video Sequences
10:30 am Break Lind Hall 400
11:00 am-12:00 pm Shashi Shekhar
University of Minnesota
Clustering oriented Storage and Access Methods
2:00 pm Clement Yu
University of Illinois at Chicago
An Efficient and Effective Metasearch Engine
3:00 pm Break Lind Hall 400
3:30 pm Peter Enser
University of Brighton
In Quest of Visual Imagery
4:30-5:30 pm Discussion Interaction Models
WEDNESDAY, FEBRUARY 28
All talks are in Lind Hall 409 unless otherwise noted.
9:15 am Coffee Lind Hall 400
9:30 am Lucy Nowell
Pacific Northwest National Laboratory
Visualization for Digital Libraries: Usability Is Not Utility
10:30 am Break Lind Hall 400
11:00 am-12:00 pm Wesley W. Chu
UCLA

Medical Digital Library to Support Scenario Specific Information Retrieval

Slides   pdf    html

2:00 pm Ed H. Chi
Xerox PARC

Scent of the Web

Slides   pdf    html

3:00 pm Break Lind Hall 400
3:30-4:30 pm Discussion Authoring and Management
THURSDAY, MARCH 1
All talks are in Lind Hall 409 unless otherwise noted.
9:15 am Coffee Lind Hall 400
9:30 am Edward J. Delp
Purdue University

Image and Video Databases: Who Cares?

Slides   pdf    html

10:30 am Break Lind Hall 400
11:00 am-12:00 pm Xiang Sean Zhou
University of Illinois at Urbana-Champaign
Relevance Feedback Techniques in Content-based Image Retrieval
2:00 pm Arnon Amir
IBM Almaden Research Center

Video Retrieval and Browsing: Research and Applications

3:00 pm Break Lind Hall 400
3:30 pm Yann LeCun
AT&T

Compressing, Delivering, and Indexing Scanned Document Collections through Content Analysis Techniques

4:30-5:30 pm Discussion

Applications

6:00 pm Workshop Dinner Lind Hall 400
FRIDAY, MARCH 2
All talks are in Lind Hall 409 unless otherwise noted.
9:00 am Coffee Lind Hall 400
9:10 am Charles Bouman
Purdue University
Image Database Search and Browsing
10:10 am Break Lind Hall 400
11:00 am-12:10 pm Michael Smith
AVA Media Inc.
Video Characterization for Browsing and Summarization
2:00 pm Neil Day
Digital Garage Inc.
MPEG-7 Applications: Multimedia Content Retrieval

Slides  html   pdf.gz (106MB)
uncompressed pdf (138MB)

Monday Tuesday

LIST OF CONFIRMED PARTICIPANTS
(in addition to postdocs and long-term participants)

As of 2/27/2001
Name Department Affiliation
Arnon Amir   IBM Almaden Research Center
P. Anandan Vision Technology Group Microsoft Research
Sankar Basu   IBM T.J. Watson Research Center
Daniel Boley Computer Science & Engineering University of Minnesota
Charles Bouman Elec. & Comp. Engineering Purdue University
Igor Chechelnitsky Computer Science University of Minnesota
Xiaoyan Cheng Computer Science University of Minnesota
Ed Chi   Xerox PARC
Wesley W. Chu Computer Science UCLA
Neil Day Strategic Research & Development Digital Garage Inc.
Edward Delp Electrical Engineering Purdue University
Peter Enser Head of Information Management University of Brighton
David Forsyth EECS University of California - Berkeley
Arif Ghafoor Elec. & Comp. Eng. Purdue University
Bryan Goodman Ford Research Laboratories M.D. 2122/SRL Ford Motor Company
Peg Howland Computer Science & Engineering University of Minnesota
Moon-Gu Jeon Computer Science University of Minnesota
Yunjae Jung Computer Science and Engineering University of Minnesota
George Karypis Computer Science & Engineering University of Minnesota
Hyejoo Kim Statistics Seoul National University
Jinseog Kim Statistics Seoul National University
Yann LeCun Head, Image Processing Research AT&T Labs - Research
B.S. Manjunath Electrical & Computer Engineering University of California Santa Barbara
Thomas Montgomery Ford Research Laboratory, MD 2122 SRL Ford Motor Company
Lucy T. Nowell SAVI Group Pacific Northwest National Laboratory
Francois Pachet   SONY CSL-Paris
Haesun Park Computer Science & Engineering University of Minnesota
Seth Patinkin Mathematics Princeton University
Peter Pirolli   Xerox PARC
Michael Roddy Computer Science University of Minnesota
Shashi Shekhar Computer Science University of Minnesota
Michael Smith   AVA Media Inc.
Paul Thomposon NEO West Group
Clement Yu Electrical Engineering & Computer Science University of Illinois at Chicago
Sean Zhou Beckman Institute of Advanced Science & Techn. University of Illinois at Urbana-Champaign

2000-2001 Program: Mathematics in Multimedia

Talk Abstracts   Material from Talks

Back to top of page
Connect With Us:
Go