Advances in Multimedia Modeling: 13th International Multimedia Modeling Conference, MMM 2007, Singapore, January 9-12, 2007, Proceedings, Part I

ISBN-13: 9783540694212 / Angielski / Miękka / 2006 / 797 str.

Tat-Jen Cham; Jianfei Cai; Chitra Dorai

Opis

The two volume set LNCS 4351 and LNCS 4352 constitutes the refereed proceedings of the 13th International Multimedia Modeling Conference, MMM 2007, held in Singapore in January 2007. Based on rigorous reviewing, the program committee selected 123 carefully revised full papers of the main technical sessions and 33 revised full papers of four special sessions from a total of 392 submissions for presentation in two volumes.

Spis treści

Learning Semantic Concepts.- Temporal Video Segmentation on H.264/AVC Compressed Bitstreams.- Ontology-Based Annotation of Paintings Using Transductive Inference Framework.- Interactive Visual Object Extraction Based on Belief Propagation.- Modeling Modifications of Multimedia Learning Resources Using Ontology-Based Representations.- Graphics.- Region-Based Reconstruction for Face Hallucination.- A Shape Distribution for Comparing 3D Models.- 3D Facial Modeling for Animation: A Nonlinear Approach.- Normalization and Alignment of 3D Objects Based on Bilateral Symmetry Planes.- Image Registration, Matching and Texture.- Extraction of Anatomic Structures from Medical Volumetric Images.- Dual-Space Pyramid Matching for Medical Image Classification.- An Image Registration Method Based on the Local and Global Structures.- Automated Segmentation of Drosophila RNAi Fluorescence Cellular Images Using Graph Cuts.- Human-Computer Interaction.- Recommendation of Visual Information by Gaze-Based Implicit Preference Acquisition.- The 3D Sensor Table for Bare Hand Tracking and Posture Recognition.- Legible Collaboration System Design.- Presentation of Dynamic Maps by Estimating User Intentions from Operation History.- Tracking and Motion Analysis.- An Object Tracking Scheme Based on Local Density.- Modeling Omni-Directional Video.- Temporally Integrated Pedestrian Detection from Non-stationary Video.- Visual Perception Theory Guided Depth Motion Estimation.- Advanced Media Coding and Adaptation.- Adaptive Data Retrieval for Load Sharing in Clustered Video Servers.- A User-Friendly News Contents Adaptation for Mobile Terminals.- An Efficient Predictive Coding of Integers with Real-Domain Predictions Using Distributed Source Coding Techniques.- A Distributed Video Coding Scheme Based on Denoising Techniques.- Media Annotation.- Fusion of Region and Image-Based Techniques for Automatic Image Annotation.- Automatic Refinement of Keyword Annotations for Web Image Search.- Mining Multiple Visual Appearances of Semantics for Image Annotation.- Automatic Video Annotation and Retrieval Based on Bayesian Inference.- Image and Video Coding.- Density-Based Image Vector Quantization Using a Genetic Algorithm.- Multilayered Contourlet Based Image Compression.- Iterative Image Coding Using Hybrid Wavelet-Based Triangulation.- A Novel Video Coding Framework by Perceptual Representation and Macroblock-Based Matching Pursuit Algorithm.- Context-Aware Media Modeling.- MetaXa—Context- and Content-Driven Metadata Enhancement for Personal Photo Books.- Context-Sensitive Ranking for Effective Image Retrieval.- Visual Verification of Historical Chinese Calligraphy Works.- Discovering User Information Goals with Semantic Website Media Modeling.- Multimedia Databases.- Online Surveillance Video Archive System.- Hierarchical Indexing Structure for 3D Human Motions.- Similarity Searching Techniques in Content-Based Audio Retrieval Via Hashing.- Fast Answering k-Nearest-Neighbor Queries over Large Image Databases Using Dual Distance Transformation.- Media Retrieval.- Subtrajectory-Based Video Indexing and Retrieval.- DR Image and Fractal Correlogram: A New Image Feature Representation Based on Fractal Codes and Its Application to Image Retrieval.- Cross-Modal Interaction and Integration with Relevance Feedback for Medical Image Retrieval.- A New Multi-view Learning Algorithm Based on ICA Feature for Image Retrieval.- P2P Networks.- A P2P Architecture for Multimedia Content Retrieval.- Optimizing the Throughput of Data-Driven Based Streaming in Heterogeneous Overlay Network.- LSONet: A Case of Layer-Encoded Video Transmission in Overlay Networks.- A Strategyproof Protocol in Mesh-Based Overlay Streaming System.- Semantic Video Concepts.- Utility-Based Summarization of Home Videos.- Performance Analysis of Multiple Classifier Fusion for Semantic Video Content Indexing and Retrieval.- Video Semantic Concept Detection Using Multi-modality Subspace Correlation Propagation.- Enhancing Comprehension of Events in Video Through Explanation-on-Demand Hypervideo.- Audio and Video Coding.- Low-Complexity Binaural Decoding Using Time/Frequency Domain HRTF Equalization.- Complexity Reduction of Multi-frame Motion Estimation in H.264.- A Novel Intra/Inter Mode Decision Algorithm for H.264/AVC Based on Spatio-temporal Correlation.- Switchable Bit-Plane Coding for High-Definition Advanced Audio Coding.- Content I.- Neighborhood Graphs for Semi-automatic Annotation of Large Image Databases.- Bridging the Gap Between Visual and Auditory Feature Spaces for Cross-Media Retrieval.- Film Narrative Exploration Through the Analysis of Aesthetic Elements.- Semantic Image Segmentation with a Multidimensional Hidden Markov Model.- Semi-supervised Cast Indexing for Feature-Length Films.- Linking Identities and Viewpoints in Home Movies Based on Robust Feature Matching.- An Efficient Automatic Video Shot Size Annotation Scheme.- Content Based Web Image Retrieval System Using Both MPEG-7 Visual Descriptors and Textual Information.- Applications I.- A New Method to Improve Multi Font Farsi/Arabic Character Segmentation Results: Using Extra Classes of Some Character Combinations.- Modeling Television Schedules for Television Stream Structuring.- Automatic Generation of Multimedia Tour Guide from Local Blogs.- Computer Vision.- A Robust 3D Face Pose Estimation and Facial Expression Control for Vision-Based Animation.- Hierarchical Shape Description Using Skeletons.- Motion Structure Parsing and Motion Editing in 3D Video.- Tamper Proofing 3D Motion Data Streams.- Image Processing I.- A Uniform Way to Handle Any Slide-Based Presentation: The Universal Presentation Controller.- A Tensor Voting for Corrupted Region Inference and Text Image Segmentation.- A Novel Coarse-to-Fine Adaptation Segmentation Approach for Cellular Image Analysis.- Vehicle Classification from Traffic Surveillance Videos at a Finer Granularity.- A Fuzzy Segmentation of Salient Region of Interest in Low Depth of Field Image.