Advances in Multimedia Modeling
17th International Multimedia Modeling Conference, MMM 2011, Taipei, Taiwan, January 5-7, 2011, Proceedings, Part II
Published on 10. January 2011
XXIII, 492 pages
978-3-642-17829-0 (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 II
Book
12/2010
1st Edition
Springer
€53.49
Shipment within 5-7 days
Content
- Title
- Preface
- Organization
- Table of Contents
- Special Session Papers
- Content Analysis for Human-Centered Multimedia Applications
- Generative Group Activity Analysis with Quaternion Descriptor
- Introduction
- Quaternion Descriptor for Activity Representation
- Appearance Component of Quaternion
- Dynamic Component of Quaternion
- Causality and Feedback Components
- Generative Activity Analysis
- Generative Activity Modeling
- Generative Activity Recognition
- Interaction Pattern Exploration and Discovery Based on Generative Model
- Experiments
- Recognition Performance on HOHA Database
- Recognition Performance on HGA Database
- Interaction Pattern Exploration and Discovery
- References
- Grid-Based Retargeting with Transformation Consistency Smoothing
- Introduction
- Visual Retargeting Framework
- Retargeting Transformation in Either Local or Global Manner
- On the Effectiveness of a Retargeting Method
- Grid Based Image Retargeting
- Importance Map
- Grid-Based Resizing Model
- Experiments
- Conclusion and Discussions
- References
- Understanding Video Sequences through Super-Resolution
- Introduction
- The Notation of Super-Resolution
- Image Registration and Prior Distribution
- The Adaptive Simultaneous Approach
- Overview of This Adaptive Simultaneous Method
- Reference Image Selection
- Median-Value Image
- Learning Prior Parameters via Weighted Cross-Validation
- Experiments Results
- Conclusion
- References
- Facial Expression Recognition on Hexagonal Structure Using LBP-Based Histogram Variances
- Introduction
- Hexagonal Histogram Variance Face (HHVF)
- Fiducial Point Detection and Face Alignment
- Conversion from Square Structure to Hexagonal Structure
- Preprocessing and LBP Texturising
- Earth Mover's Distance (EMD)
- Histogram Variances
- Classifying HHVF Images Using PCA+SVMs
- PCA Dimensionality Reduction
- SVMs Training and Recognition
- Experiments
- Dataset
- HHVFs Generation
- Training and Recognition
- Discussion
- Conclusions
- References
- Mining Social Relationship from Media Collections
- Towards More Precise Social Image-Tag Alignment
- Introduction
- Image Similarity Characterization
- Image Clustering
- Image and Tag Alignment
- Tag Correlation Network
- Random Walk for Relevance Refinement
- Algorithm Evaluation
- Conclusions
- References
- Social Community Detection from Photo Collections Using Bayesian Overlapping Subspace Clustering
- Introduction
- Social Closeness
- Community Detection Using BOSC
- BOSC Overview
- BOSC for Distance Matrix
- Experiment Results
- Conclusions
- References
- Dynamic Estimation of Family Relations from Photos
- Introduction
- Estimation of People's Relations
- What Can Be Obtained with Image Analysis
- Constructing a Relation Tree
- Estimation of the Evolution in People's Relations
- Dynamic Relation Tree - One Kind of Life Log
- Discovery of Current Status and Changes in the Family Circle
- Experiments and Discussions
- Conclusions and Future Work
- References
- Large Scale Rich Media Data Management
- Semi-automatic Flickr Group Suggestion
- Introduction
- Approach
- Image Features
- Group Classifier Building
- Representative Image Selection
- Experiments
- Data and Methodologies
- Evaluation of Group Classifiers
- Evaluation of Group Inference
- Conclusion
- References
- A Visualized Communication System Using Cross-Media Semantic Association
- Introduction
- Related Work
- Framework
- Image Recommendation
- Google Translation and NLP
- Multi-phrase Concept Detector
- Re-ranking
- Sentiment Analysis
- Experiments
- The Accuracy of the Semantic Activity Concept Detectors
- User Interface of Visualized Communication System
- The User Study
- Conclusion
- References
- Effective Large Scale Text Retrieval via Learning Risk-Minimization and Dependency-Embedded Model
- Introduction
- Learning RDRF Ranker
- Ranking Functions as Random Variables
- Risk-Minimization Based RDRF Ranker
- Experiments
- Evaluation Sets
- System Setup and Evaluation Metrics
- Result Analysis
- Related Work
- Conclusion
- References
- Efficient Large-Scale Image Data Set Exploration: Visual Concept Network and Image Summarization
- Introduction
- Data Collection, Feature Extraction and Similarity Measurement
- Visual Concept Network Generation
- Image Summarization Algorithm
- System Visualization and Evaluation
- Conclusion
- References
- Multimedia Understanding for Consumer Electronics
- A Study in User-Centered Design and Evaluation of Mental Tasks for BCI
- Introduction
- User-Centered Design: What Users Want
- User Evaluation Methodology
- Weekly Sessions and Measurements
- EEG Analysis and Mapping
- Results
- Which Mental Tasks Do Users Prefer and Why?
- What Is the Influence of Recognition Performance on Task Preference?
- Correlations between Preference and User Experience
- Discussion
- Conclusions
- References
- Video CooKing: Towards the Synthesis of Multimedia Cooking Recipes
- Introduction
- Composing a Database of Video Clips Depicting Cooking Operations
- Text Processing: Extracting Cooking Operations and Corresponding Ingredients
- Image Processing: Classifying the Video Clips Depicting Cooking Operations from the Cook Show
- Integration: Tagging the Video Clips Depicting Cooking Operations
- Experiment
- Video CooKing: A Prototype Multimedia Cooking Recipe Interface
- Conclusion
- References
- Snap2Read: Automatic Magazine Capturing and Analysis for Adaptive Mobile Reading
- Introduction
- The Method
- Page Segmentation
- Zone Classification
- Mobile Adaptation
- Experimental Results
- Magazine Dataset
- Page Segmentation and Zone Classification Performance
- Conclusion and Future Works
- References
- Multimodal Interaction Concepts for Mobile Augmented Reality Applications
- Introduction
- Interaction Concepts and Tasks
- User Study
- Results
- Conclusion
- References
- Image Object Recognition and Compression
- Morphology-Based Shape Adaptive Compression
- Introduction
- Proposed Morphological Segmentation Using Erosion
- Quantization of the Coefficients
- Coding Technique of the Image Object
- Simulation Results and Performance Comparison
- Conclusions
- References
- People Tracking in a Building Using Color Histogram Classifiers and Gaussian Weighted Individual Separation Approaches
- Introduction
- People Tracking in a Building Floor Plan
- Experimental Result
- Conclusions
- References
- Human-Centered Fingertip Mandarin Input System Using Single Camera
- Introduction
- The Proposed System
- Fingertip Detection and Tracking
- Mandarin Phonetic Symbol Recognition
- Experimental Results
- Conclusions
- References
- Automatic Container Code Recognition Using Compressed Sensing Method
- Introduction
- Compressed Sensing
- Pattern Recognition Using Compressed Sensing
- Container Code Recognition System
- Experimental Results
- Conclusions
- References
- Combining Histograms of Oriented Gradients with Global Feature for Human Detection
- Introduction
- Related Work
- Approach Overview
- HOGs-Based Human Detector
- Histogram of Oriented Gradients
- Learning of Human Detector
- Head Contour Detection
- Feature Combination
- Head Distribution Modeling
- Combination Algorithm
- Experiment
- Database Description
- Performance Evaluation
- Conclusion
- References
- Interactive Image and Video Search
- Video Browsing Using Object Trajectories
- Introduction
- Related Work
- Motion Trajectory Clustering
- Approach
- Evaluation
- Representation and Grouping of Object Trajectories
- Description
- Object Trajectory Grouping
- Evaluation
- Visualization and Browsing
- Video Browsing Tool
- Integrating Moving Object Information
- Conclusion and Future Work
- References
- Size Matters! How Thumbnail Number, Size, and Motion Influence Mobile Video Retrieval
- Introduction
- Related Work
- Interfaces for Traditional Video Retrieval
- Interfaces for Mobile Video Retrieval
- Thumbnails for Mobile Video Retrieval Interfaces
- User Study with Varying Numbers and Sizes of Thumbnails
- Motivation and Setup
- Experiment
- Results
- Conclusion and Design Suggestions
- References
- An Information Foraging Theory Based User Study of an Adaptive User Interaction Framework for Content-Based Image Retrieval
- Introduction
- uInteractFramework
- Four-Factor User Interaction Model
- uInteract Interface
- User Study Methodology
- Main Performance Indicators and Nine Hypothesis of Quantitative Analysis
- Quantitative Data Analysis Procedure
- Evaluation Results and Analysis
- Effects of the Task Environment
- Effects of the Information Environment
- Conclusions and Future Work
- References
- Poster Session Papers
- Generalized Zigzag Scanning Algorithm for Non-square Blocks
- Introduction
- First Rule for Scanning - Normalized by Size
- Second Rule for Scanning - Neighboring Coefficient
- Simulations
- Conclusions
- References
- The Interaction Ontology Model Supporting the Virtual Director Orchestrating Real-Time Group Interaction
- Introduction and Related Work
- Real-Time Scenarios
- Black Box View
- Input Primitives
- Static Setup Configuration
- Audiovisual Analysis Cues
- Game Engine State
- Interaction Ontology Specification
- Design Rationale
- Core Concepts
- Applying Reasoning
- Discussion
- References
- CLUENET: Enabling Automatic Video Aggregation in Social Media Networks
- Introduction
- Architecture
- Clues Collection
- Clues Management
- Automatic Aggregation Model
- User Query
- The Automatic Aggregation Model
- Implementation and Measurement
- Conclusions
- References
- Pedestrian Tracking Based on Hidden-Latent Temporal Markov Chain
- Introduction
- Related Works
- Pedestrian Tracking Based on Hidden-Latent Temporal Markov Chain Inference (HL-TMC)
- Time-Varying Motion Model
- Temporal-Inference Observation Model
- Time-Independent Probabilistic Latent Semantic Analysis (pLSA) Model
- Experiments and Discussion
- Tracking Performance Comparison
- Conclusion
- References
- Motion Analysis via Feature Point Tracking Technology
- Introduction
- SIFT Algorithm and Application
- Application of SIFT Algorithm
- Trajectory of Object
- Presentation of Trajectory
- Similarity between Trajectories
- System Architecture
- Experiments
- Conclusion
- References
- Traffic Monitoring and Event Analysis at Intersection Based on Integrated Multi-video and Petri Net Process
- Introduction
- Rationale of Petri Net and Multi-viewpoint Traffic Model
- Rationale of Petri Net
- Rationale of 3D Video and Multi-viewpoint Traffic Model
- Traffic Monitor and Event Analysis
- Preprocess of Traffic Videos
- Combination of Petri Net and Motion Vector Analysis
- Experimental Results and Discussion
- Experimental Results
- Discussions
- Conclusion
- References
- Baseball Event Semantic Exploring System Using HMM
- Introduction
- Proposed Framework
- Color Conversion
- Object Detection
- Play Region Classification
- HMM Training for Baseball Events
- Baseball Event Classification
- Experiments
- Conclusions
- References
- Robust Face Recognition under Different Facial Expressions, Illumination Variations and Partial Occlusions
- Introduction
- Observation Vector Extraction
- Local Binary Patterns (LBP)
- Sliding Block
- 2D Discrete Cosine Transform (2D-DCT)
- Delta DCT Cofficients
- Embedded HMM Based Face Recognition
- Experimental Results
- AR Face Database
- Experimental Setup
- Results and Discussion
- Conclusions
- References
- Localization and Recognition of the Scoreboard in Sports Video Based on SIFT Point Matching
- Introduction
- Related Work
- Proposed Scoreboard Localization and Recognition Method
- Localization Process
- Scoreboard Text Recognition
- Experiment Results
- Conclusions
- References
- 3D Model Search Using Stochastic Attributed Relational Tree Matching
- Introduction
- Related Works
- Stochastic ART Matching
- Stochastic ARG Matching
- Stochastic ART Matching
- Experiments
- Conclusion and Future Works
- References
- A Novel Horror Scene Detection Scheme on Revised Multiple Instance Learning Model
- Introduction
- Horror Scene Detection as MIL Problem
- Learning Method
- Multiple Distance - EMDD (MD-EMDD)
- Labeled with Ranking- MD - EMDD (LR-MD-EMDD)
- Experiments
- Dataset
- Experiment Set-Up
- Results
- Conclusions
- References
- Randomly Projected KD-Trees with Distance Metric Learning for Image Retrieval
- Introduction
- Randomly Projected KD-Trees
- Random Projection
- The KD-Tree Data Structure
- Algorithm
- Complexity Analysis
- Enhancing RP-KD-Trees by Distance Metric Learning
- Experiments
- Data Sets and Experimental Settings
- Performance Evaluation of RP-KD-Trees
- Comparison against Other Methods
- Evaluation of Enhanced RP-kd-Trees with DML
- Conclusions
- References
- A SAQD-Domain Source Model Unified Rate Control Algorithm for H.264 Video Coding
- Introduction
- Proposed R-SAQD Model
- Model Justification
- Link SAQD with Quantization Step
- Rate Control Scheme
- Experimental Results
- Conclusions
- References
- A Bi-objective Optimization Model for Interactive Face Retrieval
- Introduction
- The Relevance Feedback Model
- Bi-objective Optimization Model
- Top-Bottom Search for Candidates
- Experimental Analysis
- Conclusions
- References
- Multi-symbology and Multiple 1D/2D Barcodes Extraction Framework
- Introduction
- Automatic Barcodes Segmentation
- Background Small Clutters Elimination
- Potential Barcodes Segmentation
- Barcode Verification
- Experimental Results
- Conclusion
- References
- Wikipedia Based News Video Topic Modeling for Information Extraction
- Introduction
- State of the Art
- Wikipedia-Based Topic Modeling
- Topic Modeling
- Video Story Similarity Matching
- Search Framework
- Experimental Analysis
- Data
- Broad Queries
- Specific Queries
- Discussions
- References
- Advertisement Image Recognition for a Location-Based Reminder System
- Introduction
- System Overview
- Identifying Advertisement Images
- Image Feature Extraction
- Near-Duplicate Recognition
- Experimental Results
- Scalability
- Conclusion and Future Work
- References
- Flow of Qi: System of Real-Time Multimedia Interactive Application of Calligraphy Controlled by Breathing
- Introduction
- The Measuring Method and Real-Time Signal Processing Algorithm
- The Measuring Method
- Real-Time Signal Processing Algorithm
- Relation between Breathing and Calligraphy
- Conclusion
- References
- Measuring Bitrate and Quality Trade-Off in a Fast Region-of-Interest Based Video Coding
- Introduction
- Motion-Based ROI Detection
- Experiment Setup
- Bitrate Modeling
- Quality Modeling
- Discussion
- Conclusion
- References
- Image Annotation with Concept Level Feature Using PLSA+CCA
- Introduction
- Prior Work
- Approach
- Outline
- Training Data Search
- PLSA-Mixed Concept Feature
- Annotation Using PLSA-CCA
- Experiment
- Conclusion
- References
- Multi-actor Emotion Recognition in Movies Using a Bimodal Approach
- Introduction
- Related Works
- Using Low-Level Features
- Using High-Level Features
- Facial Expression Recognition (FER)
- Dealing with Large Variations in Facial Pose
- Lexical Analysis of Dialogs
- Fusing Visual and Lexical Cues
- Finding Weights
- Experimental Results and Discussions
- Dataset
- Speaker Detection
- Facial Expression Recognition
- Experiments Combining Visual and Lexical Cues
- Conclusion
- References
- Demo Session Papers
- RoboGene: An Image Retrieval System with Multi-Level Log-Based Relevance Feedback Scheme
- Introduction
- Approach
- Demonstration
- References
- Query Difficulty Guided Image Retrieval System
- Introduction
- SystemOverview
- Demonstrations
- References
- HeartPlayer: A Smart Music Player Involving Emotion Recognition, Expression and Recommendation
- Introduction
- Figure
- Music Library
- Calculating Program
- Contribution
- References
- Immersive Video Conferencing Architecture Using Game Engine Technology
- Introduction
- Video Conferencing Using Game Engine Technology
- Conclusions
- References
- Author Index
