Session O1: Interactive Image and Video Retrieval -- Interactive Experiments in Object-Based Retrieval -- Learned Lexicon-Driven Interactive Video Retrieval -- Mining Novice User Activity with TRECVID Interactive Retrieval Tasks -- Session O2: Semantic Image Retrieval -- A Linear-Algebraic Technique with an Application in Semantic Image Retrieval -- Logistic Regression of Generic Codebooks for Semantic Image Retrieval -- Query by Semantic Example -- Session O3: Visual Feature Analysis -- Corner Detectors for Affine Invariant Salient Regions: Is Color Important? -- Keyframe Retrieval by Keypoints: Can Point-to-Point Matching Help? -- Local Feature Trajectories for Efficient Event-Based Indexing of Video Sequences -- Session O4: Learning and Classification -- A Cascade of Unsupervised and Supervised Neural Networks for Natural Image Classification -- Bayesian Learning of Hierarchical Multinomial Mixture Models of Concepts for Automatic Image Annotation -- Efficient Margin-Based Rank Learning Algorithms for Information Retrieval -- Session O5: Image and Video Retrieval Metrics -- Leveraging Active Learning for Relevance Feedback Using an Information Theoretic Diversity Measure -- Video Clip Matching Using MPEG-7 Descriptors and Edit Distance -- Video Retrieval Using High Level Features: Exploiting Query Matching and Confidence-Based Weighting -- Session O6: Machine Tagging -- Annotating News Video with Locations -- Automatic Person Annotation of Family Photo Album -- Finding People Frequently Appearing in News -- Session P1: Poster I -- A Novel Framework for Robust Annotation and Retrieval in Video Sequences -- Feature Re-weighting in Content-Based Image Retrieval -- Objectionable Image Detection by ASSOM Competition -- Image Searching and Browsing by Active Aspect-Based Relevance Learning -- FindingFaces in Gray Scale Images Using Locally Linear Embeddings -- ROI-Based Medical Image Retrieval Using Human-Perception and MPEG-7 Visual Descriptors -- Hierarchical Hidden Markov Model for Rushes Structuring and Indexing -- Retrieving Objects Using Local Integral Invariants -- Retrieving Shapes Efficiently by a Qualitative Shape Descriptor: The Scope Histogram -- Relay Boost Fusion for Learning Rare Concepts in Multimedia -- Comparison Between Motion Verbs Using Similarity Measure for the Semantic Representation of Moving Object -- Coarse-to-Fine Classification for Image-Based Face Detection -- Using Topic Concepts for Semantic Video Shots Classification -- A Multi-feature Optimization Approach to Object-Based Image Classification -- Eliciting Perceptual Ground Truth for Image Segmentation -- Session P2: Poster II -- Asymmetric Learning and Dissimilarity Spaces for Content-Based Retrieval -- Video Navigation Based on Self-Organizing Maps -- Fuzzy SVM Ensembles for Relevance Feedback in Image Retrieval -- Video Mining with Frequent Itemset Configurations -- Using High-Level Semantic Features in Video Retrieval -- Recognizing Objects and Scenes in News Videos -- Face Retrieval in Broadcasting News Video by Fusing Temporal and Intensity Information -- Multidimensional Descriptor Indexing: Exploring the BitMatrix -- Natural Scene Image Modeling Using Color and Texture Visterms -- Online Image Retrieval System Using Long Term Relevance Feedback -- Perceptual Distance Functions for Similarity Retrieval of Medical Images -- Using Score Distribution Models to Select the Kernel Type for a Web-Based Adaptive Image Retrieval System (AIRS) -- Semantics Supervised Cluster-Based Index for Video Databases -- Semi-supervised Learning for Image Annotation Based on Conditional Random Fields -- NPIC: HierarchicalSynthetic Image Classification Using Image Search and Generic Features -- Session A: ASU Special Session -- Context-Aware Media Retrieval -- Estimating the Physical Effort of Human Poses -- Modular Design of Media Retrieval Workflows Using ARIA -- Image Rectification for Stereoscopic Visualization Without 3D Glasses -- Human Movement Analysis for Interactive Dance -- Session D: Demo Session -- Exploring the Dynamics of Visual Events in the Multi-dimensional Semantic Concept Space -- VideoSOM: A SOM-Based Interface for Video Browsing -- iBase: Navigating Digital Library Collections -- Exploring the Synergy of Humans and Machines in Extreme Video Retrieval -- Efficient Summarizing of Multimedia Archives Using Cluster Labeling -- Collaborative Concept Tagging for Images Based on Ontological Thinking -- Multimodal Search for Effective Video Retrieval -- MediAssist: Using Content-Based Analysis and Context to Manage Personal Photo Collections -- Mediamill: Advanced Browsing in News Video Archives -- A Large Scale System for Searching and Browsing Images from the World Wide Web -- Invited Talks -- Embrace and Tame the Digital Content -- Discovering a Fish in a Forest of Trees - False Positives and User Expectations in Visual Retrieval: Experiments in CBIR and the Visual Arts.

This volume contains the proceeding of the 5th International Conference on - age and Video Retrieval (CIVR), July 13-15, 2006, Arizona State University, Tempe, AZ, USA: http://www. civr2006. org. Image and video retrieval cont- ues to be one of the most exciting and fast-growing research areas in the ?eld of multimedia technology. However, opportunities for exchanging ideas between researchers and users of image and video retrieval systems are still limited. The InternationalConferenceonImageandVideo Retrieval(CIVR)hastakenonthe mission of bringing together these communities to allow researchers and prac- tioners around the world to share points of view on image and video retrieval. A uniquefeatureoftheconferenceistheemphasisonparticipationfrompractiti- ers. The objective is to illuminate critical issues and energize both communities for the continuing exploration of novel directions for image and video retrieval. We receivedover 90 submissions for the conference. Eachpaper wascarefully reviewed by three members of the program committee, and then checked by one of the program chairs and/or general chairs. The program committee consisted of more than 40 experts in image and video retrieval from Europe, Asia and North America, and we drew upon approximately 300 high-quality reviews to ensure a thorough and fair review process. The paper submission and review process was fully electronic, using the EDAS system. The quality of the submitted papers was very high, forcing the committee members to make some di?cult decisions. Due to time and space constraints, we could only accept 18 oral papers and 30 poster papers.