Cognitive Vision

Weareverypleasedtopresenttheproceedingsofthe4thInternationalCognitive Vision Workshop,held as part of the 6th InternationalConference on Computer Vision Systems on Santorini,Greeceduring May1215,2008.The aim of ICVW 2008 was to document the progress of the relatively young ?eld of cognitive computer vision, bringing together researchers working and interested in this ?eld and giving them a platform to discuss the results of the di?erent European cognitive vision projects as well as international projects in this area. Original research papers were solicited in all aspects of cognitive vision, targeting the following areas in particular: Memory: The coupling between visual perception, tasks, knowledge and the visualsystemrequiresmemory.Issuesthatareofspecialimportanceforin- grating memory into vision systems include: how to manage representations with limited resources;modelfor attention;integrationofinformationacross 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 adapting to unexpected changes. Also, there is a need for integration of multiple - sual 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 speci?c - ject instances, events and actions. Whereas recently some progress has been achieved in systems that allow limited recognition of object classes, events and scenes across visual appearance, new methods are needed to enable abstractions and e?ective categorization across variations in color, surface markings, geometry, temporal scenes, context and tasks.

Klappentext

This volume constitutes the post-conference proceedings of the 4th International Cognitive Vision Workshop, ICVW 2008, held in Santorini, Greece, on May 12, 2008.

The 11 papers presented were carefully reviewed and selected from 17 submissions. They cover important aspects of cognitive vision like face recognition, activity interpretation, attention, memory maps and scene interpretation.

Inhalt
Face Recognition and Activity Interpretation.- Face Recognition with Biologically Motivated Boosted Features.- A New Method for Synthetic Face Generation Using Spline Curves.- Epipolar Geometry for Humanoid Robotic Heads.- Monitoring Activities of Daily Living (ADLs) of Elderly Based on 3D Key Human Postures.- Attention, Search and Maps.- Remembering Pictures of Real-World Images Using Eye Fixation Sequences in Imagery and in Recognition.- Towards a Model of Information Seeking by Integrating Visual, Semantic and Memory Maps.- An Entropy-Based Approach to the Hierarchical Acquisition of Perception-Action Capabilities.- The Role of Implicit Context Information in Guiding Visual-Spatial Attention.- Scene Interpretation.- Probabilistic Pose Recovery Using Learned Hierarchical Object Models.- Semantic Reasoning for Scene Interpretation.- Object Detection for a Humanoid Robot Using a Probabilistic Global Workspace.