[vslist] Workshop on Visual Attention - WAPCV 2004 - Technical Program
Paletta, Lucas
lucas.paletta@joanneum.at
Wed Apr 14 08:35:01 2004
-----------------------------------------------------
<<< Announcement of Technical Program >>>
-----------------------------------------------------
WAPCV 2004=20
2nd International Workshop on=20
Attention and Performance in Computational Vision
http://dib.joanneum.at/wapcv2004
May 15, 2004
Prague, Czech Republic
Associated to ECCV 2004=20
http://cmp.felk.cvut.cz/eccv2004/
-----------------------------------------------------
WAPCV 2004 is supported by ECVision -
European Research Network for Cognitive Computer Vision Systems
http://www.ecvision.org/home/Home.htm
REGISTRATION
Please register at the official ECCV2004 web site =
(http://cmp.felk.cvut.cz/eccv2004/).
Note that registration for WAPCV is *independent* on registration for =
ECCV, however, you may
register for both events.
ORGANISING COMMITTEE
Lucas Paletta, JOANNEUM RESEARCH, Austria
John K. Tsotsos, York University, Canada
Erich Rome, Fraunhofer AIS, Germany
Glyn W. Humphreys, University of Birmingham, UK
PROGRAM COMMITTEE
Minoru Asada, Osaka University, Japan
Gerriet Backer, Krauss Software GmbH, Germany
Marlene Behrmann, Carnegie Mellon University, USA
Leonardo Chelazzi, University of Verona, Italy
James J. Clark, McGill University, Canada
Bruce A. Draper, Colorado State University, USA
Jan-Olof Eklundh, Royal Institute of Technology, Sweden
Robert B. Fisher, University of Edinburgh, UK
Horst-Michael Gross, Technical University Ilmenau, Germany
Fred Hamker, University of Muenster, Germany
John M. Henderson, Michigan State Univ., USA
Laurent Itti, University of Southern California, USA
Christof Koch, California Institute of Technology, USA
Bastian Leibe, ETH Zurich, Switzerland
Michael Lindenbaum, Technion, Israel
Nikos Paragios, ENPC Paris, France
Sajit Rao, University of Genova, Italy
Ronald A. Rensink, University of British Columbia, Canada
Antonio Torralba, MIT, USA
Jeremy Wolfe, Harvard University, USA
Hezy Yeshurun, Tel-Aviv University, Israel
SCOPE
Recently, cognitive psychology has discovered attention mechanisms to =
play a key role in object recognition and scene interpretation, =
resulting in innovative computational attention architectures modelling =
human perception. The development of enabling technologies such as video =
surveillance systems, miniaturised mobile sensors, and ambient =
intelligence systems involves the real-time analysis of enormous =
quantities of data. Knowledge has to be applied about what needs to be =
attended to, and when, and what to do in a meaningful sequence, in =
correspondence with visual feedback. Concurrently, the fundamental need =
for cognitive vision methodologies has been broadly recognised. Methods =
on attention and control are mandatory to render computer vision systems =
more robust.=20
This workshop will provide an interdisciplinary forum to present and =
communicate methodologies and concepts from computer vision, cognitive =
psychology, autonomous systems research and neuroscience with respect to =
theory and application of visual attention. We expect investigations to =
focus on computational models of attention, to outline relevant =
objectives for performance comparison, to document and to investigate =
promising application domains, and to discuss it with reference to other =
aspects of cognitive vision.=20
TECHNICAL PROGRAM (preliminary)
-------------------------------
INVITED TALK 1
Distributed Saliency Computations Solve the Feature Binding Problem
John K. Tsotsos
Department of Computer Science and Centre for Vision Research
York University, Toronto, Canada
Computational vision has a long history of proposing methods for =
decomposing a visual signal into its components. For example, many good =
strategies have appeared for decomposing visual motion signals. What has =
been far more elusive is how to recombine those components into a whole. =
This problem has even merited its own name - the binding problem. To =
date no realizable process has appeared to solve the binding problem, =
even in part, although several proposals are being studied. This =
presentation will focus on a new strategy utilizing a novel distributed =
saliency computation mechanism that solves at least one aspect of the =
binding problem, namely the binding of features from separate =
representations into a whole. Several examples will be drawn from a new, =
biologically realistic, motion analysis system, one that attends to =
complex motion patterns. An example of how this approach even yields =
Treisman-style illusory conjunctions is included. The entire process is =
implemented and operates on real image sequences. The implications for =
the neurobiology of visual attention will round out the presentation.
=20
SESSION 1: ATTENTION IN OBJECT AND SCENE RECOGNITION
Visual Attention Using Hierarchical Object Detection
Ola Ramstrom and Henrik I. Christensen
Royal Institute of Technology, Sweden=20
Inherent Limitations of Visual Search and the Role of Inner-Scene =
Similarity=20
Tamar Avraham and Michael Lindenbaum
Technion Haifa, Israel=20
SESSION 2: ARCHITECTURES FOR SEQUENTIAL ATTENTION
Selective Attention for Identification Model (SAIM): Simulating =
Different Types of Visual Neglect
Dietmar Heinke and Glyn W. Humphreys
University of Birmingham, UK=20
A Model of Object-Based Attention That Guides Active Visual Search to =
Behaviourally Relevant Locations=20
Linda J. Lanyon and Susan L. Denham
University of Plymouth, UK=20
Learning of Position and Attention-Shift Invariant Recognition across =
Attention Shifts=20
Muhua Li and James J. Clark
McGill University, Canada=20
INVITED TALK 2
The Computational Neuroscience of Visual Cognition: Attention, Memory =
and Reward
Gustavo Deco
Institucio Catalana de Recerca i Estudis Avancats (ICREA)
Universitat Pompeu Fabra, Barcelona, Spain
Cognitive behaviour requires complex context-dependent processing of =
information that emerges from the links between attentional perceptual =
processes, working memory and reward-based evaluation of the performed =
actions. We describe a computational neuroscience theoretical framework =
which shows how an attentional state held in a short term memory in the =
prefrontal cortex can by top-down processing influence ventral and =
dorsal stream cortical areas using biased competition to account for =
many aspects of visual attention. We also show how within the prefrontal =
cortex an attentional bias can influence the mapping of sensory inputs =
to motor outputs, and thus play an important role in decision making. We =
also show how the absence of expected rewards can switch the attentional =
bias signal, and thus rapidly and flexibly alter cognitive performance. =
This theoretical framework incorporates spiking and synaptic dynamics =
which enable single neuron responses, fMRI activations, psychophysical =
results, the effects of pharmacological agents, and the effects of =
damage to parts of the system, to be explicitly simulated and predicted. =
This computational neuroscience framework provides an approach for =
integrating different levels of investigation of brain function, and for =
understanding the relations between them. The models also directly =
address how bottom-up and top-down processes interact in visual =
cognition, and show how some apparently serial processes reflect the =
operation of interacting parallel distributed systems.
=20
SESSION 3: BIOLOGICALLY PLAUSIBLE MODELS FOR ATTENTION
Modeling Attention: From Computational Neuroscience to Computer Vision=20
Fred H. Hamker
Westfaelische Wilhelms-Universitaet, Germany=20
Towards a Biologically Plausible Active Visual Search Model=20
Andrei Zaharescu, Albert L. Rothenstein and John K. Tsotsos
York University, Canada=20
SESSION 4: APPLICATIONS OF ATTENTIVE VISION
Visual Attention for Object Recognition in Spatial 3D Data=20
Simone Frintrop, Andreas Nuechter, and Hartmut Surmann
Fraunhofer AIS Institute, Germany=20
AttentiRobot: A Visual Attention-based Landmark Selection Approach for =
Mobile Robot Navigation=20
Nabil Ouerhani and Heinz Huegli
University of Neuchatel, Switzerland=20
Detection of Frequent Change in Focus of Human Attention from Videos
Nan Hu, Weimin Huang, and Surendra Ranganath
Institute for Infocomm Research, Singapore=20
POSTER SESSION
On the Usefulness of Attention for Object Recognition
Dirk Walther, Ueli Rutishauser, Christof Koch, and Pietro Perona=20
California Institute of Technology, CA=20
Combining Conspicuity Maps for hROIs Prediction
Claudio M. Privitera, Orazio Gallo, Giorgio Grimoldi, Toyomi Fujita, and =
Lawrence W. Stark
University of California, Berkeley, CA=20
A General Purpose Neural Network Simulator for Visual Attention Modeling
Albert L. Rothenstein, Andrei Zaharescu, and John K. Tsotsos
York University, Canada=20
Biologically Motivated Selective Attention for Face Localization=20
Minho Lee and Sang-Woo Ban
Kyungpook National University, South Korea=20
Accumulative Computation Method for Motion Features Extraction in =
Dynamic Selective Visual Attention
Antonio Fernandez-Caballero, Mar=EDa T. L=F3pez, Miguel A. Fern=E1ndez, =
Jos=E9 Mira, Ana E. Delgado and Jos=E9 M. L=F3pez-Valles
Universidad de Castilla-La Mancha, Spain=20
Attentive Object Detection Using an Information Theoretic Saliency =
Measure
Gerald Fritz, Christin Seifert, Lucas Paletta, and Horst Bischof
JOANNEUM RESEARCH, Austria=20
Graz University of Technology, Austria
CONTACT
Lucas Paletta
JOANNEUM RESEARCH - Institute of Digital Image Processing=20
Wastiangasse 6, A-8010 Graz, Austria=20
Phone : +43 (316) 876-1769 / Fax: +43 (316) 876-91769=20
Mobile: +43 699 1876 1769=20
lucas.paletta@joanneum.at / http://dib.joanneum.ac.at/cape=20
We apologize if you received multiple copies of this message.