Introductory Remarks -- Introductory Remarks -- I Foundations of Cognitive Vision Systems -- The Space of Cognitive Vision -- Cognitive Vision Needs Attention to Link Sensing with Recognition -- Organization of Architectures for Cognitive Vision Systems -- Cognitive Vision Systems: From Ideas to Specifications -- II Recognition and Categorization -- A System for Object Class Detection -- Greedy Kernel Principal Component Analysis -- Many-to-Many Feature Matching in Object Recognition -- Integrating Video Information over Time. Example: Face Recognition from Video -- Interleaving Object Categorization and Segmentation -- III Learning and Adaptation -- Learning an Analysis Strategy for Knowledge-Based Exploration of Scenes -- IV Representation and Inference -- Things That See: Context-Aware Multi-modal Interaction -- Hierarchies Relating Topology and Geometry -- Cognitive Vision: Integrating Symbolic Qualitative Representations with Computer Vision -- On Scene Interpretation with Description Logics -- V Control and Systems Integration -- A Framework for Cognitive Vision Systems or Identifying Obstacles to Integration -- Visual Capabilities in an Interactive Autonomous Robot -- VI Conclusions -- On Sampling the Spectrum of Approaches Toward Cognitive Vision Systems.