Media Understanding -- A Novel Approach for Filtering Junk Images from Google Search Results -- Object-Based Image Retrieval Beyond Visual Appearances -- MILC2: A Multi-Layer Multi-Instance Learning Approach to Video Concept Detection -- Poster I -- An Implicit Active Contour Model for Feature Regions and Lines -- New Approach for Hierarchical Classifier Training and Multi-level Image Annotation -- Extracting Text Information for Content-Based Video Retrieval -- Real-Time Video Surveillance Based on Combining Foreground Extraction and Human Detection -- Detecting and Clustering Multiple Takes of One Scene -- An Images-Based 3D Model Retrieval Approach -- 'Oh Web Image, Where Art Thou?' -- Complementary Variance Energy for Fingerprint Segmentation -- Similarity Search in Multimedia Time Series Data Using Amplitude-Level Features -- Sound Source Localization with Non-calibrated Microphones -- PriSurv: Privacy Protected Video Surveillance System Using Adaptive Visual Abstraction -- Distribution-Based Similarity for Multi-represented Multimedia Objects -- A Multimodal Input Device for Music Authoring for Children -- Free-Shaped Video Collage -- Aesthetics-Based Automatic Home Video Skimming System -- Using Fuzzy Lists for Playlist Management -- Tagging Video Contents with Positive/Negative Interest Based on User's Facial Expression -- Snap2Play: A Mixed-Reality Game Based on Scene Identification -- Real-Time Multi-view Object Tracking in Mediated Environments -- Reconstruct 3D Human Motion from Monocular Video Using Motion Library -- Poster II -- Appropriate Segment Extraction from Shots Based on Temporal Patterns of Example Videos -- Fast Segmentation of H.264/AVC Bitstreams for On-Demand Video Summarization -- Blurred Image Detection and Classification -- Cross-Lingual Retrieval of Identical News Events by Near-Duplicate Video Segment Detection -- Web Image Gathering with a Part-Based Object Recognition Method -- A Query Language Combining Object Features and Semantic Events for Surveillance Video Retrieval -- Semantic Quantization of 3D Human Motion Capture Data Through Spatial-Temporal Feature Extraction -- Fast Intermode Decision Via Statistical Learning for H.264 Video Coding -- A Novel Motion Estimation Method Based on Normalized Cross Correlation for Video Compression -- Curved Ray-Casting for Displacement Mapping in the GPU -- Emotion-Based Music Visualization Using Photos -- LightCollabo: Distant Collaboration Support System for Manufacturers -- Accurate Identifying Method of JPEG2000 Images for Digital Cinema -- Optimization of Spatial Error Concealment for H.264 Featuring Low Complexity -- Temporal Error Concealment for H.264 Using Optimum Regression Plane -- Transform Domain Wyner-Ziv Codec Based on Turbo Trellis Codes Modulation -- Selective Sampling Based on Dynamic Certainty Propagation for Image Retrieval -- Local Radon Transform and Earth Mover's Distances for Content-Based Image Retrieval -- Content Based Querying and Searching for 3D Human Motions -- Bi-modal Conceptual Indexing for Medical Image Retrieval -- Audio Analysis for Multimedia Retrieval from a Ubiquitous Home -- Effectiveness of Signal Segmentation for Music Content Representation -- Probabilistic Estimation of a Novel Music Emotion Model -- Acoustic OFDM: Embedding High Bit-Rate Data in Audio.