[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[ProgSoc] Distinguished Lecture Series on Multimedia Processing (fwd)
Might be of interest to some....
------------------------------------------------------------------------
Peter Meric pmeric@nospam.cs.usyd.edu.au
pmeric@nospam.progsoc.uts.edu.au
http://www.progsoc.uts.edu.au/~pmeric
---------- Forwarded message ----------
Date: Tue, 28 Jul 1998 13:19:16 +1000
From: Helene Orr <helene@nospam.cs.usyd.edu.au>
To: dept@nospam.cs.usyd.edu.au
Subject: Distinguished Lecture Series on Multimedia Processing
>
>--------------------------------------------------------------------------
>
> Distinguished Lecture Series on Multimedia Processing
>
>--------------------------------------------------------------------------
>
>Date : Friday, 14 August 1998
>Presenter : > Thomas S. Huang (Univ of Illinois)
> > Alex Pentland (MIT)
>Venue : Room U215, Old Teacher's College, The Unversity of Sydney
>Fees : . A$140.00 for one lecture, Students A$60.00, including
> lecture note, lunch, and morning or afternoon tea/coffee.
> . A$250.00 for two lectures, Students A$100.00, including both
> lecture notes, lunch, morning and afternoon tee/coffee.
> . 20% discount for group registration of 5 or more people.
>
>-------------------------------------------------------------------------
>
>LECTURE 1: Multimedia Signal Processing
>
>Presenter: THOMAS S. HUANG
> Beckman Institute for Advanced Science and Technology
> University of Illinois at Urbana-Champaign
>
>Time: 8:30am-12:00pm
>
>ABSTRACT
>
>Multimedia refers to information representation: text, speech, images,
>video, graphics, etc. Multimodality refers to human-computer interface:
>Visual, audio, tactile, etc. In this lecture, we shall describe research
>in two areas:
>
>1) Multimodal human-computer interface:
>
>We are especially interested in the integration of speech and vision
>in human-computer interface. Several projects will be discussed -
>Combining speech and bare-hand gesture in controlling display; Using
>visual lip reading to enhance audio speech recognition in noisy
>environments; and bimodal (visual and audio) emotion recognition.
>One underlying question is what are good ways of fusing visual and
>audio cues in pattern recognition. We shall describe several
>Hidden Markov Model based architectures and compare the performance.
>
>2) Multimedia databases:
>
>Of particular interest are image and video databases. Topics to be
>discussed include: Example-based image retrieval using similarity in
>color, texture, shape, and layout. Using relevance feedback to make
>the database system adaptive to user intentions. Constructing
>semantic Table-of-Contents and Index for video.
>
>
>Biography of THOMAS S. HUANG
>
>Thomas S. Huang received his Sc.D. Degrees in Electrical Engineering
>from the Massachusetts Institute of Technology. He was on the
>Faculty of the Department of Electrical Engineering at MIT from 1963
>to 1973; and on the Faculty of the School of Electrical Engineering
>and Director of its Laboratory for Information and Signal Processing
>at Purdue University from 1973 to 1980. In 1980, he joined the
>University of Illinois at Urbana-Champaign, where he is now William
>L. Everitt Distinguished Professor of Electlrical and Computer
>Engineering, and Research Professor at the Coordinated Science
>Laboratory, and Head of the Image Formation and Processing Group at
>the Beckman Institute for Advanced Science and Technology.
>
>During his sabbatical leaves: Dr. Huang has worked at the MIT Lincoln
>Laboratory, the IBM Thomas J. Watson Research Center, and the Rheinishes
>Landes Museum in Bonn, West Germany, and held visiting Professor
>positions at the Swiss Institutes of Technology in Zurich and Lausanne,
>University of Hannover in West Germany, INRS-Telecommunications of
>the University of Quebec in Montreal, Canada and University of Tokyo,
>Japan. He has served as a consultant to numerous industrial firms and
>government agencies both in the U.S. and abroad.
>
>Dr. Huang's professional interests lie in the broad area of information
>technology, especially the transmission and processing of multidimensional
>signals. He has published 12 books, and over 300 papers in Network Theory,
>Digital Filtering, Image Processing, and Computer Vision. He is a Fellow
>of the International Association of Pattern Recognition, IEEE, and the
>Optical Society of American; and has received a Guggenheim Fellowship ,
>an A.V. Humboldt Foundation Senior U.S. Scientist Award, and a Fellowship
>from the Japan Association for the Promotion of Science. He received the
>IEEE Signal Processing Society's Technical Achievement Award in 1987, and
>the Society Award in 1991. He is a Founding Editor of the International
>Journal Computer Vision, Graphics, and Image Processing; and Editor of
>the Springer Series in Information Sciences, published by Springer Verlag.
>
>-----------------------------------------------------------------------
>
>LECTURE 2: Adaptive Multimodal Systems for Communications and Situation
> Understanding
>
>Presenter: ALEX PENTLAND
> Academic Head, MIT Media Laboratory
> Massachusetts Institute of Technology
>
>Time: 1:30pm-5:00pm
>
>Abstract
>
>I will describe a series of real-time systems that are able to (1)
>track human's hand/head/body motions and their voice output, (2) learn
>their typical patterns of behavior, (3) detect anomalous behaviors,
>and finally, to (4) react to the situation. Tracking is done in 3D
>within a Baysian modeling framework employing low-dimensional image
>appearance models. Behavior learning and anomaly detection is
>accomplished using Baysian graphical models, including traditional
>HMMs and our new Coupled HMMs, and makes use of our new Conditional EM
>modeling methods.
>
>Application include: real-time systems for reading Sign Language,
>teaching T'ai Chi, detecting interactions between people in
>survellance data, and word learning from examples.
>
>One particularly interesting example is a WEARABLE computer that
>learns the wearer's typical behviors via camera and microphone. By
>knowing what the user is doing, the wearable computer can become
>a real `personal digital assistant,' anticipating both communications
>and information needs.
>
>
>Biography of ALEX P. PENTLAND
>
>Alex Paul Pentland is the Academic Head of the M.I.T. Media Laboratory. He
>is also the Toshiba Professor of Media Arts and Sciences, an endowed chair
>last held by Marvin Minsky. He has done research in wearable computing,
>human-machine interface, computer graphics, artificial intelligence, machine
>and human vision, and has published more than 180 scientific articles in
>these areas. His most recent research focus is understanding human behavior
>in video, including face, expression, gesture, and intention recognition,
>as described in the April 1996 issue of Scientific America. He has won awards
>from AAAI, IEEE, and Ars Electronica. Newsweek magazine has recently named
>him one of the 100 Americans most likely to shape the next century.
>
>
>For more information, please contact:
>
>Dr. Ling Guan
>Dept of Electrical Engineering
>University of Sydney
>Sydney, NSW 2006
>tel: 61-2-9351-2154
>fax: 61-2-9351-3847
>email: ling@nospam.ee.usyd.edu.au
>
>-------------------------------------------------------------------
>
> Distinguished Lecture Series Registration Form
>
>
>Name:_____________________________Tel:_____________Fax:_____________
>
>Email:______________________________________________________________
>
>Address:____________________________________________________________
>
>City:_______________State:________________Postal/Zip Code___________
>
>Country:__________________________________
>
>
>Please make the cheque payable to "The University of Sydney"
>
>Send to: Jose Lay, School of Electrical and Information Engineering,
> Building J-03, University of Sydney, NSW 2006 Australia
>
Helene Orr helene@nospam.cs.usyd.edu.au
Admin Officer Phone: +61 2 9351 4158
Basser Department of Computer Science Fax: +61 2 9351 3838
University of Sydney
NSW 2006 AUSTRALIA
--
You are subscribed to the progsoc mailing list. To unsubscribe, send a
message containing "unsubscribe" to progsoc-request@nospam.progsoc.uts.edu.au.
If you are having trouble, ask owner-progsoc@nospam.progsoc.uts.edu.au for help.
This list is archived at <http://www.progsoc.uts.edu.au/lists/progsoc/>