Advances in Multimedia Modeling 15th International Multimedia Modeling Conference, MMM 2009, Sophia-Antipolis, France, January 7-9, 2009. Proceedings.

th Welcome to the 15 International Multimedia Modeling Conference (MMM 2009), held January 7–9, 2009 at EURECOM, Sophia-Antipolis, France. MMM is a leadinginternationalconference for researchersandindustry practitionersto share their new ideas, original research results and practical development ex- riences from all multimedia-related areas. MMM 2009 was held in co-operation with the ACM Special Interest Group on MultiMedia (ACM SIGMM). It was a great honor to host MMM 2009, one of the most long-standing th multimedia conferences, at EURECOM in Sophia-Antipolis, France. The 15 edition of MMM marked the return of the conference to Europe after numerous years of activity in Asia, and we are proud to have organized such a prestigious conference on the French Riviera. EURECOM is an engineering school in the domain of information and communication technology and a research center in communication systems. Since its creation in 1991 by TELECOM ParisTech and EPFL, it has developed strong international links with both academic and industrial partners. The heart of EURECOM is its internationally renowned research activities which focus on three areas: networking and security, mobile communications, and multimedia.

Searching and Finding in Large Video Collections.- Structuring and Accessing Semantic Multimedia Data.- Adaptive Model for Integrating Different Types of Associated Texts for Automated Annotation of Web Images.- SenseCam Image Localisation Using Hierarchical SURF Trees.- General Highlight Detection in Sport Videos.- Probabilistic Integration of Tracking and Recognition of Soccer Players.- A Fast and Fully Format Compliant Protection of JPEG2000 Code-Streams.- Towards a New Image-Based Spectrogram Segmentation Speech Coder Optimised for Intelligibility.- Robust 3D Face Tracking on Unknown Users with Dynamical Active Models.- A Fast Hybrid Decision Algorithm for H.264/AVC Intra Prediction Based on Entropy Theory.- Low Complexity Video Compression Using Moving Edge Detection Based on DCT Coefficients.- Converting H.264-Derived Motion Information into Depth Map.- A Novel Approach for Fast and Accurate Commercial Detection in H.264/AVC Bit Streams Based on Logo Identification.- Bit Allocation for Spatio-temporal Wavelet Coding of Animated Semi-regular Meshes.- Modeling the Quantizer Behavior of Subbands for Data Rate Limitations in JPEG2000.- Performance and Waiting-Time Predictability Analysis of Design Options in Cost-Based Scheduling for Scalable Media Streaming.- Evaluating Streaming Rate Controllers: A Support Tool.- Graph-Based Pairwise Learning to Rank for Video Search.- Comparison of Feature Construction Methods for Video Relevance Prediction.- Large Scale Concept Detection in Video Using a Region Thesaurus.- Multimedia Evidence Fusion for Video Concept Detection via OWA Operator.- Personalized Image Recommendation.- Online Macro-segmentation of Television Streams.- A Real-Time Content Based Video Copy Detection System.- Active Objects in Interactive Mobile TV.- Sparse Multiscale Patches (SMP) for Image Categorization.- Multiple-Instance Active Learning for Image Categorization.- A New Multiple Kernel Approach for Visual Concept Learning.- Integrating Image Segmentation and Classification for Fuzzy Knowledge-Based Multimedia Indexing.- Variability Tolerant Audio Motif Discovery.- Key Estimation Using Circle of Fifths.- Feature Analysis and Normalization Approach for Robust Content-Based Music Retrieval to Encoded Audio with Different Bit Rates.- A Multimodal Constellation Model for Object Category Recognition.- Robust Visual Content Representation Using Compression Modes Driven Low-level Visual Descriptors.- Spatial Hierarchy of Textons Distributions for Scene Classification.- Approximate Retrieval with HiPeR: Application to VA-Hierarchies.- A Novel Multi-reference Points Fingerprint Matching Method.- HVPN: The Combination of Horizontal and Vertical Pose Normalization for Face Recognition.- 3D Multimedia Data Search System Based on Stochastic ARG Matching Method.- 3D Face Recognition Using R-ICP and Geodesic Coupled Approach.- Mining Association Patterns between Music and Video Clips in Professional MTV.- Semi-supervised Learning of Caricature Pattern from Manifold Regularization.- An Image Inpainting Algorithm Based on Local Geometric Similarity.- Evidence Theory-Based Multimodal Emotion Recognition.- Sketch-on-Map: Spatial Queries for Retrieving Human Locomotion Patterns from Continuously Archived GPS Data.- Personalized News Video Recommendation.- Facet-Based Browsing in Video Retrieval: A Simulation-Based Evaluation.- A User Experience Model for Home Video Summarization.