Advances in Multimedia Modeling
17th International Multimedia Modeling Conference, MMM 2011, Taipei, Taiwan, January 5-7, 2011, Proceedings, Part I
Published on 10. January 2011
XXIII, 562 pages
978-3-642-17832-0 (ISBN)
Description
This two-volume proceedings constitutes the refereed papers of the 17th International Multimedia Modeling Conference, MMM 2011, held in Taipei, Taiwan, in January 2011. The 51 revised regular papers, 25 special session papers, 21 poster session papers, and 3 demo session papers, were carefully reviewed and selected from 450 submissions. The papers are organized in topical sections on audio, image video processing, coding and compression; media content browsing and retrieval; multi-camera, multi-view, and 3D systems; multimedia indexing and mining; multimedia content analysis; multimedia signal processing and communications; and multimedia applications. The special session papers deal with content analysis for human-centered multimedia applications; large scale rich media data management; multimedia understanding for consumer electronics; image object recognition and compression; and interactive image and video search.
More details
Other editions
Additional editions
Kuo-Tien Lee | Wen-Hsiang Tsai | Hong-Yuan Mark Liao
Advances in Multimedia Modeling
17th International Multimedia Modeling Conference, MMM 2011, Taipei, Taiwan, January 5-7, 2011, Proceedings, Part I
Book
12/2010
Springer
€96.29
Article exhausted; check different version
Content
- Title
- Preface
- Organization
- Table of Contents - Part I
- Regular Papers
- Audio, Image, Video Processing, Coding and Compression
- A Generalized Coding Artifacts and Noise Removal Algorithm for Digitally Compressed Video Signals
- Introduction
- Local Entropy Calculation
- Compression Artifacts and Noise Removal
- Results and Evaluation
- Conclusion
- References
- Efficient Mode Selection with BMA Based Pre-processing Algorithms for H.264/AVC Fast Intra Mode Decision
- Introduction
- Overview of Intra Prediction and Mode Decision
- Proposed Intra-mode Pre-processing Selection Algorithm
- Pixel-Based Block Matching Algorithm (PBMA)
- Block-Based Block Matching Algorithm (BBMA)
- Experimental Results, Comparisons and Discussions
- Comparison of Proposed and Previous Algorithms
- Discussion for Encoding Time Reduction
- Conclusion
- References
- Perceptual Motivated Coding Strategy for Quality Consistency
- Introduction
- Proposed Method
- Problem Analysis
- Distortion Model
- New D-Q Model
- Region Partition
- Our Proposed Scheme
- Experimental Results and Analysis
- Conclusions
- References
- Compressed-Domain Shot Boundary Detection for H.264/AVC Using Intra Partitioning Maps
- Introduction
- Related Work
- General Techniques
- Algorithms for H.264/AVC
- Intra Partitioning Maps
- Performance Results
- Conclusions
- References
- Adaptive Orthogonal Transform for Motion Compensation Residual in Video Compression
- Introduction
- Problem Formulation
- The Proposed Algorithm
- Overall Experiments and Results
- Conclusion
- References
- Parallel Deblocking Filter for H.264/AVC on the TILERA Many-Core Systems
- Introduction
- Short Overview of TILERA Many-Core Systems
- Deblocking Filter and the Wavefront Method
- The Proposed MB-Level Deblocking Filter
- Experimental Results
- Conclusion
- References
- Image Distortion Estimation by Hash Comparison
- Introduction
- Image Distortion Estimation
- An Image Hash Algorithm for Distortion Estimation
- SNR Estimation
- Experiment Results
- Improve Estimation Accuracy
- Conclusion
- References
- Media Content Browsing and Retrieval
- Sewing Photos: Smooth Transition between Photos
- Introduction
- Related Work
- Field Study
- Participants and Method
- Results and Findings
- Framework of Buffer Region
- Observation
- Buffer Region
- General Method
- System
- System Overview
- Clustering Photos
- Guessing Camera Operations
- Extracting ROIs and Buffer Regions
- Calculating Camera Path
- Generating Slideshow
- Evaluation
- Conclusion
- References
- Employing Aesthetic Principles for Automatic Photo Book Layout
- Introduction
- Related Work
- Aesthetic Principles for Photo Books
- Spatial Layout
- Color Layout
- Automatic Photo Album Layout
- Preprocessing
- Content Distribution
- Background Layout
- High-Level Foreground Layout
- Detailed Foreground Layout
- Application
- Conclusion
- References
- Video Event Retrieval from a Small Number of Examples Using Rough Set Theory
- Introduction
- Addressed Problems
- Large Variation of Features in the Same Event
- High-Dimensional, Small Sample Size Problem
- Example-Based Event Retrieval Method
- Experimental Results
- Conclusion and Future Works
- References
- Community Discovery from Movie and Its Application to Poster Generation
- Introduction
- Approach to Community Discovery from a Movie
- Face Grouping
- Community Graph Construction
- Application to Video Poster Generation
- Key Role Identification
- Poster Generation
- Experiment
- Evaluation of Face Grouping
- Evaluation of Key Role Extraction
- Evaluation of Poster Generation
- Conclusion
- References
- A BOVW Based Query Generative Model
- Introduction
- Related Work
- Query Generative Model
- p(fd|fQ)
- p(fd|d)
- p(CQ|Q) and p(fQ|CQ)
- Experiment
- Soft Assignment
- Shot-Based Relevance
- Retrieval Performance
- Conclusion
- References
- Video Sequence Identification in TV Broadcasts
- Introduction
- Related Work
- Motion Signature
- Segment Matching Algorithm
- Evaluation
- Intra-Stream
- Resized Intra-Stream
- Inter-Stream
- Resized Inter-Stream
- Conclusion
- References
- Content-Based Multimedia Retrieval in the Presence of Unknown User Preferences
- Introduction
- Related Work
- A Novel Retrieval Approach
- Experimental Evaluation
- Conclusions and Future Work
- References
- Multi-Camera, Multi-View, and 3D Systems
- People Localization in a Camera Network Combining Background Subtraction and Scene-Aware Human Detection
- Introduction
- Problem Definition and Proposed Method
- Scene-Aware Human Detectors
- POM Generation by Background Subtraction
- Fusion of Two POMs
- Experimental Results and Discussion
- Conclusion and Future Work
- References
- A Novel Depth-Image Based View Synthes is Scheme for Multiview and 3DTV
- Introduction
- A Novel View Synthesis Scheme
- Artifact Detection and Repairing
- Experiments
- Conclusion
- References
- Egocentric View Transition for Video Monitoring in a Distributed Camera Network
- Introduction
- Related Works
- System Overview
- Preprocessing
- Multi-camera Tracking
- View Transition for Overlapping Cameras
- Foreground Detection
- Foreground Billboard Construction and Position Estimation
- Virtual Camera Placement
- View Transition for Non-overlapping Cameras
- Foreground Particles Generation
- Particles Movement Control
- Virtual Camera Placement
- Background Texture Adaptation
- Results
- Conclusions
- References
- A Multiple Camera System with Real-Time Volume Reconstruction for Articulated Skeleton Pose Tracking
- Introduction
- Previous Work
- The Multi-camera System
- System Setup
- Camera Calibration
- Volume Reconstruction
- Background Subtraction
- Shape-from-Silhouette and Visual Hulls
- Skeleton Pose Estimation
- The Body Model
- Pose Estimation and Tracking
- Results
- Conclusion
- References
- A New Two-Omni-Camera System with a Console Table for Versatile 3D Vision Applications and Its Automatic Adaptation to Imprecise Camera Setups
- Introduction
- Idea of Proposed Method
- Proposed Techniques for Camera Parameter Calibration
- Proposed Technique to Calculate the Angle between Optical Axes
- Proposed Technique to Detect a Space Line in an Omni-Image
- Calculation of the Angle between the Two Optical Axes
- Proposed Technique for Calculating 3D Data of Feature Points
- Experimental Results
- Conclusions
- References
- 3D Face Recognition Based on Local Shape Patterns and Sparse Representation Classifier
- Introduction
- The Approach Overview
- 3D Face Registration Using R-ICP
- Local Feature Extraction
- Local Binary Patterns
- Local Shape Patterns
- LSP Based Facial Representation
- SRC Classification
- Experiments and Results
- Conclusions
- References
- An Effective Approach to Pose Invariant 3DFace Recognition
- Introduction
- Related Work
- The Proposed Pose Invariant 3D Face Recognition
- Geometry Alignment via 3D Mesh Parametrization
- Locality Preserving Sparse Coding for Facial Images
- Experiments
- Experimental Testbed
- Evaluation of LPSC for 2D Face Recognition
- Evaluation of Pose Invariance Face Recognition : 2D vs. 3D
- Conclusions
- References
- Multimedia Indexing and Mining
- Score Following and Retrieval Based on Chroma and Octave Representation
- Introduction
- Related Work
- Feature Extraction
- Chroma and Octave Features
- Feature Extraction from MIDI
- Feature Extraction from Audio
- Score Following and Score Retrieval
- Music-Score Matching
- Score Retrieval
- Experiments
- Performance of Music-Score Matching
- Performance of Score Retrieval
- Conclusion
- References
- Incremental Multiple Classifier Active Learning for Concept Indexing in Images and Videos
- Introduction
- Active Learning with Multiple Classifiers
- The Proposed Incremental Method
- Experiments
- TRECVID 2007 and 2008 Collections
- Image Representation
- Optimal Negative to Positive Ratios
- The Active Learning Steps
- Active Learning Effectiveness
- Execution Times
- Conclusion
- References
- A Semantic Higher-Level Visual Representation for Object Recognition
- Introduction
- Classical Visual Word Construction
- Semantic Model for Generating the Semantic Visual Word Candidates (SVWCs)
- Generative Process
- Parameters Estimation
- Semantic Visual Word Candidates (SVWCs) Generation
- Semantic Visual Phrase Candidates (SVPCs)
- Association Rules and SVPCs Generation
- Semantic Visual Word (SVW) and Semantic Visual Phrase(SVP) Generation
- Vote-Based Classifier for Object Recognition
- Experiments
- Dataset and Experimental Setup
- Contribution between the Classical Visual Words, SVWs and SVPs
- Comparison between the Proposed Approach Performance and Similar Approaches
- Conclusion
- References
- Mining Travel Patterns from GPS-Tagged Photos
- Introduction
- Related Work
- Approach
- Building the Travel Path Database
- Transition Traffic between RoAs
- Experiments
- Travel Path Database
- Tourist Traffic Analysis
- Conclusion
- References
- Augmenting Image Processing with Social Tag Mining for Landmark Recognition
- Introduction
- Problem Statement and Proposed Approach
- Analysis of Images and Social Metadata
- Content Analysis of Images
- Analysis of User Tags
- Exploring the Number of Views
- Interestingness Measure
- Combining Multiple Heterogenous Rankings
- Evaluation of Proposed Approach
- Conclusion
- References
- News Shot Cloud: Ranking TV News Shots by Cross TV-Channel Filtering for Efficient Browsing of Large-Scale News Video Archives
- Introduction
- Related Works
- Cross TV-Channel Filtering
- Aim and Goal
- Finding News Programs
- Video Frame Comparison
- Shot Boundary Detection
- Grouping by Bipartite Graph Traversal
- Removal of Commercials
- Visualizing News Shot Cloud
- Experimental Evaluation
- TV Broadcast Archive
- Frame Comparison Method
- Computational Cost
- Size and Quality of Selected News Shots
- Conclusions
- References
- Multimedia Content Analysis (I)
- Speaker Change Detection Using Variable Segments for Video Indexing
- Introduction
- Proposed Method
- The Variable Segment Feature
- BIC Scanning Algorithm
- Cross Verification
- Experimental Result
- Discussion
- Conclusion and Future Work
- References
- Correlated PLSA for Image Clustering
- Introduction
- The PLSA Model
- Our Correlated PLSA Model
- Overview
- Bag-of-Visual-Words Representation and Image Correlations
- Parameter Estimating
- Experimental Evaluations
- Conclusions and Future Work
- References
- Genre Classification and the Invariance of MFCC Features to Key and Tempo
- Introduction
- Key Histograms of the GTZAN Dataset
- Are MFCCs Invariant to Key and Tempo?
- Mel-Frequency Cepstral Coefficients
- Key and Tempo Transformations
- Comparison of MFCCs under Key and Tempo Transforms
- Genre Classification with Musical Transforms
- Experiments
- Dataset and Experimental Setup
- Experimental Results
- Discussion
- Conclusion
- References
- Combination of Local and Global Features for Near-Duplicate Detection
- Introduction
- Methods
- Keypoint Detection and Matching
- Matching Lines Filtering Based on Affine Invariant Feature
- Confirmative Matching Using LBP and Color Histogram
- Experimental Results and Discussion
- Conclusion
- References
- Audio Tag Annotation and Retrieval Using Tag Count Information
- Introduction
- Tag Counts
- Cost-Sensitive Learning
- Cost-Sensitive Evaluation Metrics
- Cost-Sensitive Classification Methods
- Experiments
- Model Selection and Evaluation
- Experiment Results
- Conclusion
- References
- Similarity Measurement for Animation Movies
- Introduction
- Animation Film Context
- The Proposed Approach
- General Description
- Evaluation by Human Observers
- Feature Extraction
- Fusion of Feature Differences
- Experimental Results
- Conclusion
- References
- Multimedia Content Analysis (II)
- A Feature Sequence Kernel for Video Concept Classification
- Introduction
- A Kernel for MPEG-7 Visual Features
- A Kernel for Sequences of Feature Vectors
- Evaluation
- Data
- Results
- Discussion
- Conclusion and Future Work
- References
- Bottom-Up Saliency Detection Model Based on Amplitude Spectrum
- Introduction
- Approach
- Obtaining the Amplitude Values for Each Patch
- Salient Value for Each Patch
- Experiments
- Discussions and Conclusions
- References
- L2-Signature Quadratic Form Distance for Efficient Query Processing in Very Large Multimedia Databases
- Introduction
- Content Representation Forms and Similarity Measures of Multimedia Data
- L2-Signature Quadratic Form Distance
- Experimental Evaluation
- Conclusions and Outlook
- References
- Generating Representative Views of Landmarks via Scenic Theme Detection
- Introduction
- Related Work
- Our Approach
- Problem Formulation
- Dirichlet Process Gaussian Mixture Model (DPGMM)
- Experiment
- Conclusion
- References
- Regularized Semi-supervised Latent Dirichlet Allocation for Visual Concept Learning
- Introduction
- Regularized Semi-supervised LDA
- Regularization Framework
- Regularized Semi-supervised LDA Algorithm
- Experiments
- Data Preparation and Feature Extraction
- Regularized Semi-supervised LDA vs. Fully Supervised LDA
- Regularized Semi-supervised LDA vs. Simple Semi-supervised LDA
- Conclusions
- References
- Boosted Scene Categorization Approach by Adjusting Inner Structures and Outer Weights of Weak Classifiers
- Introduction
- Overview AdaBoost Algorithms
- Boosted Scene Categorization by Adjusting Inner Structures and Determining Outer Weights of Weak Classifiers
- Low-Level Feature Extraction
- Training Weak Classifiers
- Boosted Scene Categorization Approach by Adjusting Inner Structure and Outer Weights of Weak Classifiers
- Genetic Algorithm Based Parameters Optimization
- Experimental Results and Discussions
- Experimental Results on OT Dataset
- Experimental Results on Sport Event Dataset
- Performances Versus Fused Weak Classifier Number
- Conclusion
- References
- A User-Centric System for Home Movie Summarisation
- Introduction
- Proposed Home Movie Summarisation System
- Sub-shot Segmentation
- Summarisation Engine
- Interaction Design
- Initial Summarisation and Browsing Scheme
- Advanced Summarisation
- Summary Customisation: Manual Refinement
- Conclusion
- References
- Multimedia Signal Processing and Communications
- Image Super-Resolution by Vectorizing Edges
- Introduction
- Related Work
- System Overview
- Edge Forming
- Edge Detection
- Edge Extraction
- Edge Color Analysis
- Trimap Generation
- Matting
- Edge Shape Approximation
- Sub-pixel Refinement
- Edge Shape Fitting
- Polygonal Image Representation
- Computing Bézier Grid Points
- Sampling Bézier Curve Points
- Polygonal Image Representation
- Vertex Color Determination
- Edge Preserving Super Resolution
- Mean Value Coordinate
- Image Interpolation Using MVC
- Image Reblurring
- Result
- Conclusion and Future Work
- References
- Vehicle Counting without Background Modeling
- Introduction
- Vehicle Detection without Background Modeling
- Adaptive Block-Based Foreground Detection
- Precise Object Region Extraction with the Dual Foregrounds
- Foreground Segmentation
- True Object Verification
- Vehicle Tracking
- Kalman Filter
- Vehicle Counting
- Experimental Results
- The Detection of Moving Vehicles
- Vehicle Tracking and Counting
- Conclusions
- References
- Effective Color-Difference-Based Interpolation Algorithm for CFA Image Demosaicking
- Introduction
- The Proposed Scheme
- The Demosaicking Procedure of Green Plane
- Principle of Variable Naming
- The Demosaicking Procedure of R-G/B-G Color Difference Planes
- Value Estimation of the Missing Diagonal-Class R-G Pixels
- Value Estimation of the Missing Vertical-Class R-G Pixels
- Experimental Results
- Conclusions and Future Work
- References
- Utility Max-Min Fair Rate Allocation for Multiuser Multimedia Communications
- Introduction
- Utility Max-Min Fairness Description
- Video Quality-Rate Model
- Utility Max-Min Fairness Definition
- Video User's Utility Function
- Utility Max-Min Fair Rate Allocation
- Simulation Results
- Parameter Estimation
- The Criterions of Efficiency and Fairness
- Multiuser Rate Allocation
- Conclusion
- References
- Multimedia Applications
- Adaptive Model for Robust Pedestrian Counting
- Introduction
- Adaptive Model
- Part Models
- Grid Mask for Torso Detection Using Consistent Contour
- Pedestrian Detection Based on Branch Structure
- Pedestrian Verification and Optimization
- The Bayesian Framework
- RJMCMC for Pedestrian Counting
- Experiments
- Conclusion
- References
- Multi Objective Optimization Based Fast Motion Detector
- Introduction
- Multi Objective Optimization (MOO)
- Linear Weight Constraint
- Nonlinear Weight Constraint
- MOO U pdated Divided Difference Filter
- Evaluation Result
- Conclusion
- References
- Narrative Generation by Repurposing Digital Videos
- Introduction
- Video Scene Generation
- Construction of Motion Map
- Object Removal by Patch Referencing
- Panoramic Scene Construction
- Video Narrative Generation
- Avatar Segmentation
- Object Size Regulation
- Motion Interpolation and Extrapolation of Avatars
- Spatiotemporal Placement and Layer Merging
- Experiment Results
- Conclusion
- References
- A Coordinate Transformation System Based on the Human Feature Information
- Introduction
- Feature Points a nd S keleton
- Find Endpoints in Human Object
- Cluster Object by Endpoints
- Coordinate System Transform
- Find Camera Parameter Matrix
- Compute 3D Coordinate
- Experiments Result
- Conclusion
- References
- An Effective Illumination Compensation Method for Face Recognition
- Introduction
- The Proposed Illumination Compensation Method
- Homomorphic Filtering
- Ratio Image Generation
- Anisotropic Smoothing
- Experimental Results
- Conclusion
- References
- Shape Stylized Face Caricatures
- Introduction
- Related Work
- Our Prior Work
- Golden Ratio Feature Space
- Caricature Generation
- Golden Ratio Based
- Art and Psychology Stereotype Based
- Cartoon Template Based
- Image Warping
- Conclusions and Future Work
- References
- i-m-Breath: The Effect of Multimedia Biofeedback on Learning Abdominal Breath
- Introduction
- Related Work
- System Framework
- Breath Detection
- Biofeedback
- Experimental Methods
- Participants and Location
- Experimental Procedure
- Experimental Results
- Conclusions and Future Work
- References
- Author Index
