Advances in Multimedia Modeling

The 16th international conference on Multimedia Modeling (MMM2010) was held in the famous mountain city Chongqing, China, January 6–8, 2010, and hosted by Southwest University. MMM is a leading international conference for researchersand industry practitioners to share their new ideas, original research results and practicaldevelopment experiences from all multimedia related areas. MMM2010attractedmorethan160regular,specialsession,anddemosession submissions from 21 countries/regions around the world. All submitted papers were reviewed by at least two PC members or external reviewers, and most of them were reviewed by three reviewers. The review process was very selective. From the total of 133 submissions to the main track, 43 (32. 3%) were accepted as regular papers, 22 (16. 5%) as short papers. In all, 15 papers were received for three special sessions, which is by invitation only, and 14 submissions were received for a demo session, with 9 being selected. Authors of accepted papers come from 16 countries/regions. This volume of the proceedings contains the abstracts of three invited talks and all the regular, short, special session and demo papers. The regular papers were categorized into nine sections: 3D mod- ing;advancedvideocodingandadaptation;face,gestureandapplications;image processing;imageretrieval;learningsemanticconcepts;mediaanalysisandm- eling; semantic video concepts; and tracking and motion analysis. Three special sessions were video analysis and event recognition, cross-X multimedia mining in large scale, and mobile computing and applications. The technical programfeatured three invited talks, paralleloral presentation of all the accepted regular and special session papers, and poster sessions for short and demo papers.

Invited Talks.- Slow Intelligence Systems.- Media 2.0 – The New Media Revolution?.- Designing a Comprehensive Visual Recognition System.- Regular Papers.- Surface Reconstruction from Images Using a Variational Formulation.- Layer-Constraint-Based Visibility for Volumetric Multi-view Reconstruction.- Two Stages Stereo Dense Matching Algorithm for 3D Skin Micro-surface Reconstruction.- Safe Polyhedral Visual Hulls.- Enhanced Temporal Error Concealment for 1Seg Video Broadcasting.- User-Centered Video Quality Assessment for Scalable Video Coding of H.264/AVC Standard.- Subjective Experiments on Gender and Ethnicity Recognition from Different Face Representations.- Facial Parameters and Their Influence on Subjective Impression in the Context of Keyframe Extraction from Home Video Contents.- Characterizing Virtual Populations in Massively Multiplayer Online Role-Playing Games.- Browsing Large Personal Multimedia Archives in a Lean-Back Environment.- Automatic Image Inpainting by Heuristic Texture and Structure Completion.- Multispectral and Panchromatic Images Fusion by Adaptive PCNN.- A Dual Binary Image Watermarking Based on Wavelet Domain and Pixel Distribution Features.- PSF-Constraints Based Iterative Blind Deconvolution Method for Image Deblurring.- Face Image Retrieval across Age Variation Using Relevance Feedback.- Visual Reranking with Local Learning Consistency.- Social Image Search with Diverse Relevance Ranking.- View Context: A 3D Model Feature for Retrieval.- Scene Location Guide by Image-Based Retrieval.- Learning Landmarks by Exploiting Social Media.- Discovering Class-Specific Informative Patches and Its Application in Landmark Charaterization.- Mid-Level Concept Learning with Visual Contextual Ontologies and Probabilistic Inference for Image Annotation.- A Color Saliency Model for Salient Objects Detection in Natural Scenes.- Generating Visual Concept Network from Large-Scale Weakly-Tagged Images.- Automatic Image Annotation with Cooperation of Concept-Specific and Universal Visual Vocabularies.- Weak Metric Learning for Feature Fusion towards Perception-Inspired Object Recognition.- The Persian Linguistic Based Audio-Visual Data Corpus, AVA II, Considering Coarticulation.- Variational Color Image Segmentation via Chromaticity-Brightness Decomposition.- Image Matching Based on Representative Local Descriptors.- Stereoscopic Visual Attention Model for 3D Video.- Non-intrusive Speech Quality Assessment with Support Vector Regression.- Semantic User Modelling for Personal News Video Retrieval.- TV News Story Segmentation Based on Semantic Coherence and Content Similarity.- Query-Based Video Event Definition Using Rough Set Theory and High-Dimensional Representation.- Story-Based Retrieval by Learning and Measuring the Concept-Based and Content-Based Similarity.- Camera Take Reconstruction.- Semantic Based Adaptive Movie Summarisation.- Towards Annotation of Video as Part of Search.- Human Action Recognition in Videos Using Hybrid Motion Features.- Bag of Spatio-temporal Synonym Sets for Human Action Recognition.- A Novel Trajectory Clustering Approach for Motion Segmentation.- New Optical Flow Approach for Motion Segmentation Based on Gamma Distribution.- Reducing Frame Rate for Object Tracking.- Special Session Papers.- A Study on Sampling Strategies in Space-Time Domain for Recognition Applications.- Fire Surveillance Method Based on Quaternionic Wavelet Features.- Object Tracking and Local Appearance Capturing in a Remote Scene Video Surveillance System with Two Cameras.- Dual Phase Learning for Large Scale Video Gait Recognition.- Semantic Concept Detection for User-Generated Video Content Using a Refined Image Folksonomy.- Semantic Entity-Relationship Model for Large-Scale Multimedia News Exploration and Recommendation.- PageRank with Text Similarity and Video Near-Duplicate Constraints for News Story Re-ranking.- Learning Vocabulary-Based Hashing with AdaBoost.- Mediapedia: Mining Web Knowledge to Construct Multimedia Encyclopedia.- Sensing Geographical Impact Factor of Multimedia News Events for Localized Retrieval and News Filtering.- Travel Photo and Video Summarization with Cross-Media Correlation and Mutual Influence.- An Augmented Reality Tourist Guide on Your Mobile Devices.- Transfer Regression Model for Indoor 3D Location Estimation.- Personalized Sports Video Customization for Mobile Devices.- 3D Thumbnails for Mobile Media Browser Interface with Autostereoscopic Displays.- Short Papers.- Video Scene Segmentation Using Time Constraint Dominant-Set Clustering.- Automatic Nipple Detection Using Shape and Statistical Skin Color Information.- Asymmetric Bayesian Learning for Image Retrieval with Relevance Feedback.- Automatic Visualization of Story Clusters in TV Series Summary.- From Image Hashing to Video Hashing.- Which Tags Are Related to Visual Content?.- Anchor Shot Detection with Diverse Style Backgrounds Based on Spatial-Temporal Slice Analysis.- The SLDSRC Rate Control Scheme for H.264.- Adaptively Adjusted Gaussian Mixture Models for Surveillance Applications.- Estimating Poses of World’s Photos with Geographic Metadata.- Discriminative Image Hashing Based on Region of Interest.- Transformational Breathing between Present and Past: Virtual Exhibition System of the Mao-Kung Ting.- Learning Cooking Techniques from YouTube.- Adaptive Server Bandwidth Allocation for Multi-channel P2P Live Streaming.- Feature Subspace Selection for Efficient Video Retrieval.- A Novel Retrieval Framework Using Classification, Feature Selection and Indexing Structure.- Fully Utilized and Low Design Effort Architecture for H.264/AVC Intra Predictor Generation.- A Database Approach for Expressive Modeling and Efficient Querying of Visual Information.- A Multiple Instance Approach for Keyword-Based Retrieval in Un-annotated Image Database.- On the Advantages of the Use of Bitstream Extraction for Video Summary Generation.- Image Clustering via Sparse Representation.- A Parameterized Representation for the Cartoon Sample Space.- Demo Session Papers.- Enhancing Seeker-Bars of Video Players with Dominant Color Rivers.- AdVR: Linking Ad Video with Products or Service.- Searching and Recommending Sports Content on Mobile Devices.- Extended CBIR via Learning Semantics of Query Image.- A Gesture-Based Personal Archive Browser Prototype.- E-learning Web, Printing and Multimedia Format Generation Using Independent XML Technology.- Dynamic Video Collage.- VDictionary: Automatically Generate Visual Dictionary via Wikimedias.- Video Reference: A Video Question Answering Engine.