This book constitutes the thoroughly refereed post-proceedings of the Third International Workshop on Adaptive Multimedia Retrieval, held in September 2005.

The 18 revised full papers presented were carefully selected during two rounds of reviewing and improvement. Also included are three invited papers by leading researchers in the area to illustrate the core topics of the workshop: User, Context and Feedback. The papers are organized in topical sections on ranking, systems, spatio-temporal relations, using feedback, using context, and meta data.

Inhalt

Invited Contributions.- Putting the User in the Loop: Visual Resource Discovery.- Using Relevance Feedback to Bridge the Semantic Gap.- Leveraging Context for Adaptive Multimedia Retrieval: A Matter of Control.- Ranking.- Rank-Ordering Documents According to Their Relevance in Information Retrieval Using Refinements of Ordered-Weighted Aggregations.- Ranking Invariance Based on Similarity Measures in Document Retrieval.- Systems.- Developing AMIE: An Adaptive Multimedia Integrated Environment.- Exploring the Structure of Media Stream Interactions for Multimedia Browsing.- CARSA - An Architecture for the Development of Context Adaptive Retrieval Systems.- Integrating Media Management Towards Ambient Intelligence.- CANDELA - Storage, Analysis and Retrieval of Video Content in Distributed Systems.- Spatio-temporal Relations.- Interactive Retrieval of Video Sequences from Local Feature Dynamics.- Temporal Relation Analysis in Audiovisual Documents for Complementary Descriptive Information.- Using Feedback.- Using Segmented Objects in Ostensive Video Shot Retrieval.- Learning User Queries in Multimodal Dissimilarity Spaces.- Surface Features in Video Retrieval.- Toward Consistent Evaluation of Relevance Feedback Approaches in Multimedia Retrieval.- Using Context.- An Explorative Study of Interface Support for Image Searching.- Context-Based Image Similarity Queries.- Meta Data.- Information Retrieval of Sequential Data in Heterogeneous XML Databases.- A Visual Annotation Framework Using Common-Sensical and Linguistic Relationships for Semantic Media Retrieval.- Improving Access to Multimedia Using Multi-source Hierarchical Meta-data.