6th International Conference on Computer Vision Systems, Vision for Cognitive Systems

Welcome to ICVS 2008

Vision for Cognitive Systems

  • ICVW

4th International Cognitive Vision Workshop – ICVW 2008


The paper submission for the workshop is now open. Please refer to the official submission page of the workshop.

Description of the workshop

Basic visual operations such as categorization and complex tasks such as scene interpretation are major challenges for computational vision. At least some of these issues call for integration of methods into systems. Traditionally vision has been studied using a reductionistic approach. Given the complexity of cognitive tasks, however, it is not obvious that this strategy is the most efficient to address the core problems. Issues such as multi-cue integration, embodied categorization, and behavior / skill acquisition can only be studied in the context of systems. Recent progress in studies of categorization, statistical learning theory, active perception, software engineering and computational neuroscience is paving the way for improved understanding of cognitive functionalities in artificial systems.

The objectives of this workshop are:

  • Document the progress of the relatively young field of Cognitive Computer Vision and Systems.
  • Bringing together the researchers working and interested in this field and giving them a platform to discuss the results of the different European cognitive vision projects and International projects in this area.
  • Increase the visibility of Cognitive Vision internationally.

Topic Areas:

This workshop will focus on discussion of components methods such as:

  • Memory: The coupling between visual perception, tasks, knowledge and the visual system requires memory. Issues that are of special importance for integrating memory into vision systems include: how to manage representations in presence of limited resources; model for attention; integration of information across representations and time.

  • Learning and Adaptation: A system whose goal is that of interacting with the real world must be capable of learning from experience and adapt to unexpected changes. Also, there is a need for integration of multiple visual features to enable generation of stable hypotheses, and for methods for combination of cues in the presence of uncertainty.

  • Categorization: Research has in particular focused on recall of specific object instances, events and actions. Whereas recently some progress has been achieved on systems that allow limited recognition of object classes, events and scenes across visual appearance, new methods are needed to enable abstractions and effective categorization across variations in color, surface markings, geometry, temporal scenes, context and tasks.

  • Integration: Vision is often considered in isolation. When considered in the context of an embodied system the concept of an ''active visual observer''  becomes important. The visual system operates here as a task oriented perception module that generates a diverse set of visual descriptions about the environment. The set of descriptors is by no means organized in a hierarchy. Depending on the task at hand the system might generate features to the ''agent'' in terms of events, labels, and/or spatio-temporal models (geometry, trajectories, relations, etc). Thus, integration plays an important role from processing of visual cues and multi-modal sensor fusion to systems architecture.

(NEW!) Draft Schedule

Workshop Session 1: Face Recognition and Activity Interpretation
Monday, 12th May, 17:30 - 19:20

  • 17:30 Welcome
  • 17:40 Face Recognition with Biologically Motivated Boosted Features
    Berkovich Erez, Hillel Pratt and Moshe Gur
  • 18:05 A New method for Synthetic Face Generation Using Spline Curves
    Ali Borji
  • 18:30 Epipolar Geometry for Humanoid Robotic Heads
    Justin Hart, Brian Scassellati and Steven Zucker
  • 18:55 Monitoring Activities of Daily Living (ADLs) of Elderly Based on 3D Key Human Postures
    Nadia Zouba, Bernard Boulay, Francois Bremond and Monique Thonnat

Workshop Session 2: Attention, Search and Maps
Tuesday, 13th May, 09:00 - 10:40

  • 09:00 Remembering Pictures of Real-World Images Using Eye Fixation Sequences in Imagery and in Recognition
    Geoffrey Underwood, Neil Mennie, Katherine Humphrey and Jean Underwood
  • 09:25 Towards a Model of Information Seeking by Integrating Visual, Semantic and Memory Maps
    Myriam Chanceaux, Anne Guerin, Benoit Lemaire and Thierry Baccino
  • 09:50 An Entropy-based Approach to the Hierarchical Acquisition of Perception-Action Capabilities
    David Windridge, Mikhail Shevchenko and Josef Kittler
  • 10:15 The Role of Implicit Context Information in Guiding Visual-Spatial Attention
    Andrea Schankin, Olaf Stursberg and Anna Schubo
  • 10:40 Coffee Break

Workshop Session 3: Scene Interpretation
Tuesday, 13th May, 11:15 - 12:30

  • 11:15 Probabilistic Pose Recovery Using Learned Hierarchical Object Models
    Renaud Detry Nicolas Pugeault, and Justus Piater
  • 11:40 Semantic Reasoning for Scene Interpretation
    Lars Baunegaard With Jensen, Emre Baseski, Sinan Kalkan, Nicolas Pugeault and Florentin Worgotter
  • 12:05 Object Detection for a Humanoid Robot Using a Probabilistic Global Workspace
    Andreas Fidjeland, Murray Shanahan and Alexandros Bouganis
  • 12:30 Summary and Closing the Workshop

Steering Committee

Henrik Christensen, (Georgia Tech, USA)
Bruce Draper, (Colorado State University, USA)
Bernd Schiele, (Darmstadt University of Technology, D)
John K. Tsotsos, (York University, CAN)

Programm Committee

Alberto Munoz (UMDI-SISAL-UNAM, Mex)
Ales Leonardis (University of Ljubljana, Slovenia)
Bernt Schiele (TU Darmstadt, Germany)
Bruce Draper (Colorado State University, USA)
Danica Kragic (KTH, S)
Darius Burschka (TU München, D)
David Hogg (University of Leeds, UK)
David Vernon (Etisalat University College, UAE)
Gerhard Sagerer (University of Bielefeld
Giorgio Metta (University of Genova, Italy)
Hans-Hellmut Nagel (Universität Karlsruhe, Germany)
Henrik Christensen (Georgia Tech, USA)
Jeremy Wyatt (University of Birmingham, UK)
John Tsotsos (York University, Canada)
Justus Piater
Lucas Paletta (Joanneum Research, A)
Michael Felsberg (Linköping University, Sweden)
Monique Thonnat (INRIA, France)
Nick Pears (University of York)
Nikolaos Mavridis (MIT, USA)
Paul Fitzpatrick (University of Genoa, It)
Peter Auer (University of Leoben, Austria)
Ross Beveridge (Colorado State University, USA)
Václav Hlavác (CTU Prag, Cz)
Yiannis Demiris (Imperial College, UK)

Authors Information

Papers will be double blind reviewed by 3 reviewers. Accepted papers will be published n post-conference proceedings by Springer in LNCS (pending final approval).

The layout of the papers must be prepared according to the Instructions for the Preparation of Camera-Ready Contribution to LNCS Proceedings. Authors are asked to follow these instructions exactly. In addition to the Springer author instructions, authors should ensure that the submitted paper meet the following criteria.

  • The paper must not exceed 14 pages in the LNCs format. The font sizes must conform with the LNCS instructions.
  • Document formats:
    • PostScript, without encoding or condensation.
    • Level 3 or 4 PDF without passwords or encryption.
    • MS Word and other word processor formats will not be accepted.
  • The fonts used must meet the following criteria:
    • All fonts must be from Latin 1 Fontset.
    • Except for the 13 basic PostScript fonts (Times-Roman, Helvetica, Courrier, Symbol), every font used must be included.
    • If possible, include only outline (Type 1 or TrueType) fonts, not bitmapped ones.

Prepare for Double-blind Review

The first page should contain only the:

  • Title,
  • Abstract,
  • 3-5 keywords characterising the content of the paper,

The remaining pages should include the main body of the submission and all references, figures, tables, etc.

Anonymised for Blind Reviews:

  • Author name(s) should not appear in the paper (including the abstract).,
  • Eliminate references to your institutions, your sponsors, your unpublished work, and your published work if done in a way that identifies you as author.
  • All author names must be inserted in the online submission form.
  • Delete author and institution information from document properties.

Paper submission procedure and reviewing process

  • Web-based paper submission
  • Web-based review by three persons of the program committee, Effort to give a comprehensive review will be recognized with the selection of a best reviewer recognition.
  • Final consolidation and selection meeting by the Workshop chair(s) and organizing committee.
  • Immediate notification to authors.
  • Web-based selection of final camera-ready papers.

Format of the workshop (e.g., talks, posters, demos, invited speakers)

  • One (or two) invited speaker(s)
  • About 10-12 oral presentations
  • Posters depending on the quality of the submission

Workshop History and related Workshops:

  • 1st Cognitive Vision Workshop, 19 and 20 September 2002, Zürich, Switzerland
  • NIPS2003 Workshop on "Open Challenges in Cognitive Vision", 13 December 2003, Whistler, British Columbia, Canada
  • Early Cognitive Vision Workshop, 28.5. - 1.6.2004, Isle of Skye, Scotland, emphasis on biological motivated computer vision, visual neuroscience and computational neuroscience of vision
  • 1st Austrian Cognitive Vision Workshop, 31.1.2005, Zell an der Pram, Austria
  • 2nd International Cognitive Vision Workshop, 13.5.2006, Graz, Austria
  • 3rd International Cognitive Vision Workshop, 21.03.2007, Bielefeld, Germany

Important Dates

   Full Paper Submission EXPIRED 10 February 2008
   Full Paper Submission: 25 January 2008
   Acceptance Notification EXPIRED 10 March 2008
   Acceptance Notification: 28 February 2008
   Camera ready Copy (NEW!) To be announced (after the workshop)
   Camera ready Copy: 25 March 2008

Workshop organizers, contact

Barbara Caputo
IDIAP Research Institute, Centre Du Parc, A. des Pres-Beudin 20
P.O.Box 592, 1920 Martigny, Switzerland
Tel: +41 27 721 77 37
Fax: +41 27 721 77 12
E-mail: bcaputo AT idiap DOT ch
Web: http://people.idiap.ch/caputo

Markus Vincze
Automation and Control Institute, Vienna University of Technology
Gusshausstrasse 27/376, 1040 Vienna, Austria
Tel: +431/58801-37661
Fax: +431/58801-37697
E-mail: vincze AT acin.tuwien DOT ac DOT at
Web: http://www.acin.tuwien.ac.at

5th International Workshop on Attention in Cognitive Systems - WAPCV 2008

The text below is a brief description of the official workshop website. Please refer to the official page for the latest news and information concerning the workshop.


Description of the workshop

The capacity to attend to the relevant has been part of AI systems since the early days of the discipline. Currently, with respect to the design and computational modeling of artificial cognitive systems, selective attention has again become a focus of research, and one sees it important for the organization of behaviors, for control and interfacing between sensory and cognitive information processing, and for the understanding of individual and social cognition in humanoid artifacts.

While visual cognition obviously plays a central role in human perception, findings from neuroscience and cognitive psychology have informed us on the perception-action nature of cognition. In particular, the embodiment in sensory-motor intelligence requires a continuous spatio-temporal interplay between interpretations from various perceptual modalities and the corresponding control of motor activities. In addition, the process of selecting information from the incoming sensory stream, in tune with contextual processing on a current task and global goals, becomes a challenging control issue within the viewpoint of focused attention. Seemingly attention systems must operate at many levels and not only at interfaces between a bottom-up driven world interpretation and top-down driven information selection. One may consider selective attention as part of the core of artificial cognitive systems. These insights have already produced paradigmatic changes in several AI-related disciplines, such as, in the design of behavior based robotics and the computational modeling of animats.

Within the context of the engineering domain, the development of enabling technologies such as autonomous robotic systems, miniaturized mobile - even wearable - sensors, and ambient intelligence systems involves the real-time analysis of enormous quantities of data. These data have to be processed in an intelligent way to provide "on time delivery" of the required relevant information. 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.

Topic Areas:

Topics of interest include, but are not limited to, the following:

  • Techniques, modelling, and concepts:
    • Computational architectures for attention
    • Biologically inspired attention
    • Attentive control of robot systems
    • Aspects of attention in cognitive psychology, neuroscience, and philosophy
    • Attention and control of machine vision processes
    • Attention in object recognition and detection
    • Attention and contextual modelling
    • Attention in multimodal information fusion
    • Attention in affordance perception
    • Performance measures for attention enabled artificial systems
    • Machine learning and feature selection in robot perception
    • Decision making and attention
    • Robust statistical techniques for attention
    • Perceptual organisation
    • Evolutionary aspects of attention

  • Application related topics of interest:
    • Attentive multimodal interfaces
    • Attentive robotic systems
    • Autonomous intelligent systems
    • Mobile Mapping systems
    • Video surveillance
    • Video and image retrieval
    • Industrial inspection
    • Remote sensing
    • Medical computer vision
    • Usability research

(NEW!) Draft Schedule

Workshop Session 1: Spatiotemporal Saliency
Monday, 12th May, 08:45 - 10:40

  • 08:45 Chai Welcome, overview
  • 09:00 Key Note: Learning to Attend: From Bottom-Up to Top-Down
    Jochen Triesch
  • 10:00 Motion Saliency Maps from Spatiotemporal Filtering
    Anna Belardinelli, Fiora Pirri and Andrea Carbone
  • 10:20 Spatiotemporal Saliency: Towards a Hierarchical Representation of Visual Saliency Neil D. B. Bruce and John K. Tsotsos
  • 10:40 Coffee Break

Workshop Session 2: Attention in Scene Exploration
Monday, 12th May, 11:20 - 13:00

  • 11:20 On the Optimality of Spatial Attention for Object Detection
    Jonathan Harel and Christof Koch
  • 11:40 A Novel Hierarchical Framework for Object-based Visual Attention
    Rebeca Marfil, Antonio Bandera and Francisco Sandoval
  • 12:00 Information-theoretic Decision Making for Exploration of Dynamic Scenes
    Eric Sommerlade and Ian Reid
  • 12:20 Enhancing Robustness of a Saliency-based Attention System for Driver Assistance
    Thomas Michalke, Jannik Fritsch and Christian Goerick
  • 12:40 Where Do We Grasp Objects? - An Experimental Verification of the Selective Attention for Action Model
    Christoph Boehme and Dietmar Heinke

Workshop Session 3: Scene Interpretation
Monday, 12th May, 14:30 - 16:30

  • 14:30 Key Note: Brain Mechanisms of Attentional Control
    Steve Yantis
  • 15:30 Model Based Analysis of fMRI-data: Applying the sSoTS Framework to the Neural Basis of Preview Search
    Eirini Mavritsaki, Glyn Humphreys and Harriet Allen
  • 15:50 Modelling the Efficiencies and Interactions of Attentional Networks
    Fehmida Hussain and Sharon Wood
  • 16:10 Understanding the Interactions of Bottom-up and Top-down Attention for the Development of a Humanoid Robot System
    David Henderickx, Eric Soetens, and Kathleen Maetens
  • 16:30 Coffee Break

Workshop Session 4: Contexual Cueing and Saliency
Monday, 12th May, 17:00 - 18:00

  • 17:00 The Time Course of Attentional Guidance in Contextual Cueing
    Andrea Schankin, Anna Schubö
  • 17:20 Conspicuity and Congruity in Change Detection
    G. Underwood, E. Templeman and J. Underwood
  • 17:40 Probabilistic Combination of Visual Context Based Attention and Object Detection
    Roland Perko, Christian Wojek, Bernt Schiele, and Ales Leonardis

Poster Session
Monday, 12th May, 18:00 - 19:00

  • 18:00 Poster Presentations
  • Towards Standardized Metrics and Methods for Evaluation of Visual Attention Models
    Muhammad Zaheer Aziz and Bärbel Mertsching
  • Decoding What People See from Where They Look: Predicting Visual Stimuli from Scanpaths
    Moran Cerf, Jonathan Harel, Alex Huth, Wolfgang Einhäuser and Christof Koch
  • CHREST: A Computational Model of Human Attention
    Peter Lane, Fernand Gobet and Richard Smith
  • The Jamf Attention Modelling Framework
    Johannes Steger, Niklas Wilming, Felix Wolfsteller, Nicolas Höning and Peter König
  • Modeling Attention and Perceptual Grouping to Salient Objects
    Thomas Geerinck, Hichem Sahli, Iris Vanhamel and Valentin Enescu
  • Comparing Learning Attention Control In Perceptual and Decision Space
    Maryam S. Mirian, Majid Nili Ahmadabadi and Babak N. Araabi
  • A Novel Bottom-Up and Top-Down Attention Model
    Matei Mancas
  • Towards a Characterization of the Oculomotor Behavior in a Drawing Task
    Ruben Coen Cagli, Paolo Coraggio, Paolo Napoletano, Giuseppe Boccignone and Mario Ferraro
  • A Visual Novelty Detection Component for Virtual Agents
    Christopher Peters and Didier Grandjean

Programm Committee

Leonardo Chelazzi, University of Verona, Italy
James J. Clark, McGill University, Canada
J.M. Findlay, Durham University, UK
Simone Frintrop, University of Bonn, Germany
Fred Hamker, University of Muenster, Germany
Dietmar Heinke, University of Birmingham, UK
Laurent Itti, University of Southern California, CA, USA
Christof Koch, California Institute of Technology, CA, USA
Ilona Kovacs, Budapest Univ. of Technology, Hungary
Eileen Kowler, Rutgers University, NJ, USA
Michael Lindenbaum, Technion, Israel
Larry Manevitz, University of Haifa, Israel
Baerbel Mertsching, University of Paderborn, Germany
Giorgio Metta, University of Genoa, Italy
Vidhya Navalpakkam, California Institute of Technology, CA, USA
Aude Oliva, MIT, MA, USA
Kevin O'Regan, Universite de Paris 5, France
Fiora Pirri, University of Rome, La Sapienza, Italy
Marc Pomplun, University of Massachusetts Boston, USA
Catherine Reed, University of Denver, CO, USA
Ronald A. Rensink, University of British Columbia, BC, Canada
Erich Rome, Fraunhofer IAIS, Germany
John G. Taylor, King's College London, UK
Jochen Triesch, Frankfurt Institute for Advanced Studies, Germany
Nuno Vasconcelos, University of California San Diego, CA, USA
Chen Yu, University of Indiana, IN, USA
Tom Ziemke, University of Skövde, Sweden

Paper submission procedure and reviewing process

  • Dual Submission Policy
    Papers will be considered for review that are specifically submitted to WAPCV 2008 as well as those that are submitted to the main ICVS conference as well. Double submission must be indicated by authors, and the workshop organizer must be given a copy of the ICVS reviews.

  • Style
  • The format of the final paper is Springer single column. Detailed instructions about the preparation of the paper is available at the Springer publication website. Submitted papers should not exceed 14 pages in Springer format. The paper should be developed in LaTeX (see Springer LNCS author guidelines) to facilitate the book compilation process for the book proceedings. However, the submitted file should be in PDF format.

  • Double Blind Review
    All reviewing will be double blind, so the papers will not include any information which allows the authors to be identified.

  • Electronic Submission and Review Process
    For WAPCV 2008 we will provide electronic submission and review facilities. Reviewers will receive usernames and passwords, will be able to edit their review file, and submit it finally to the co-chairs. This system has already been successfully used at WAPCV 2005 and 2007, ICVW 2006, and IMV 2006.
    Electronic submission link (activated by 5 January, 2008).

  • Conference Proceedings
    On-site proceedings containing the full paper contributions will be published in a proceedings booklet in color print by JOANNEUM RESEARCH, funded by the EC Cognitive Systems unit. In addition, participants will receive a CD-ROM containing all presentations in PDF format. This procedure has been successfully applied to all WAPCV workshops.

Format of the workshop (e.g., talks, posters, demos, invited speakers)

  • Two invited speakers.
  • About 10 - 12 oral presentations.
  • 10 - 15 posters.
  • One lunch and two coffee breaks.

Workshop History and related Workshops:

WAPCV 2008 is a direct successor to WAPCV 2007 (http://dib.joanneum.at/wapcv2007), held at Hyderabad, India in association with IJCAI 2007, WAPCV 2005, WAPCV 2004 and WAPCV 2003. The first workshop in this series, WAPCV 2003 (http://dib.joanneum.at/wapcv2003), was held in Graz, Austria, associated to the ICVS2003.

Important Dates

   Full Paper Submission EXPIRED 29 January 2008
   Full Paper Submission: 20 January 2008
   Acceptance Notification EXPIRED 21 March 2008
   Acceptance Notification: 28 February 2008
   Final Paper Submission (EXPIRED) 20 April 2008
   Final Camera Submission : 25 March 2008
   Workshop Day: 12 May 2008

Workshop organizers, contact

Dr. Lucas Paletta
JOANNEUM RESEARCH Forschungsgesellschaft mbH
Institute of Digital Image Processing
Wastiangasse 6, 8010 Graz, Austria
Phone: +43 (316) 876 1769
Fax: +43 (316) 876 91769
E-mail: lucas DOT paletta AT joanneum DOT at
Web: http://dib.joanneum.at/cape

Prof. John K. Tsotsos
Department. of Computer Science & Engineering
York University
4700 Keele St., Toronto, Ont. M3J 1P3, Canada
Phone: +1 416-736-2100 - 70135
Fax: +1 416-736-5872
Email: tsotsos AT cse DOT yorku DOT ca
Web: http://www.cse.yorku.ca/~tsotsos/