Advances in Multimedia Modeling
18th International Conference, MMM 2012, Klagenfurt, Austria, January 4-6, 2012, Proceedings
Published on 3. January 2012
XX, 795 pages
978-3-642-27355-1 (ISBN)
Description
This book constitutes the refereed proceedings of the 18th International Multimedia Modeling Conference, MMM 2012, held in Klagenfurt, Austria, in January 2012. The 38 revised regular papers, 12 special session papers, 15 poster session papers, and 6 demo session papers were carefully reviewed and selected from 142 submissions. The papers are organized in the following topical sections: annotation, annotation and interactive multimedia applications, event and activity, mining and mobile multimedia applications, search, summarization and visualization, visualization and advanced multimedia systems, and the special sessions: interactive and immersive entertainment and communication, multimedia preservation: how to ensure multimedia access over time, multi-modal and cross-modal search, and video surveillance.
More details
Other editions
Additional editions
Klaus Schoeffmann | Bernard Mérialdo | Alexander G. Hauptmann
Advances in Multimedia Modeling
18th International Conference, MMM 2012, Klagenfurt, Austria, January 4-6, 2012, Proceedings
Book
12/2011
1st Edition
Springer
€53.49
Shipment within 7-9 days
Content
- Title
- Preface
- Conference Organization
- Table of Contents
- Invited Talks
- A New Gap to Bridge: Where to Go Next in Social Media Retrieval? (Extended Abstract)
- Mining Multimedia Data for Meaning
- Challenges in Serious Gaming as Emerging Multimedia Technology for Education, Training, Sports and Health
- Regular Papers
- Annotation I
- Building Semantic Hierarchies Faithful to Image Semantics
- Introduction
- Related Work
- Discussion
- Building of the Hierarchy
- Visual Similarity
- Conceptual Similarity
- Contextual Similarity
- Semantico-Visual Relatedness of Concepts (SVRC)
- Heuristic Rules for Hierarchy Building
- Experimental Result
- Visual Representation of Images
- Weighting
- Evaluation
- Conclusion
- References
- Combining Image-Level and Segment-Level Models for Automatic Ann
- Introduction
- Models Overview
- Image Label Transfer (A)
- TagProp
- Segment Label Estimation (B)
- Label Copy
- Token Model
- Label-To-Region (LTR)
- Segment Label Transfer (C)
- Token Model
- SegProp
- Image Labels from Segment Predictions (D)
- Maximum Prediction
- Global SegProp
- Joint Label Prediction
- Joint Segment-Level Prediction by Product (E)
- Joint Image-Level Prediction by Product (F)
- Tagprop + Global SegProp (F)
- Data Sets and Features
- Experimental Evaluation
- Conclusion
- References
- Multi-layer Local Graph Words for Object Recognition
- Introduction
- Graph Feature Construction
- Graph Comparison
- Visual Dictionaries
- Clustering Method
- Visual Signatures
- Experiments
- SURF Based BoW vs Graphs Words
- The Multi-layer Approach
- Conclusion and Perspectives
- References
- Multimodal Video Concept Detection via Bag of Auditory Words and Multiple Kernel Learning
- Introduction
- Related Work
- Concept Detection System
- Bag of Auditory Words
- Kernel Choice
- Multimodal Fusion
- Experimental Results
- Evaluation Criteria
- Results
- Discussion
- Conclusions
- References
- Content-Based Video Description for Automatic Video Genre Categorization
- Introduction
- Audio Descriptors
- Temporal Structure Descriptors
- Color Descriptors
- Contour Descriptors
- Experimental Results
- One Genre at a Time Classification
- Descriptor-Based Visualization
- Conclusions
- References
- Annotation II
- Towards Category-Based Aesthetic Models of Photographs
- Introduction
- Prior Art
- The Image Corpus
- Aesthetic Feature Extraction
- Simplicity Features
- Global Features
- Contrasting Region Features
- Aesthetics Models
- Category-Based Aesthetic Models
- Generic Aesthetics Model
- Experimental Results
- Conclusions and Future Work
- References
- Scene Signatures for Unconstrained News Video Stories
- Introduction
- Related Work
- Framework to Generate Scene Signature
- Keyframe Sampling and NDK Clustering
- Processing of SIFT Keypoints
- Connected Keypoint Analysis.
- Isolated Keypoint Analysis.
- Scene Signature Generation and Similarity
- Refinement of Initial Scene Signature
- Experimental Results
- Discriminative and Compactness Analyses of the Scene Signature
- Retrieval Using Scene Signature
- Conclusion
- References
- Visual Vocabulary Optimization with Spatial Context for Image Annotation and Classification
- Introduction
- Motivation
- Our Approach
- Experiments
- Conclusion
- References
- Colorization Using Quaternion Algebra with Automatic Scribble Generation
- Introduction
- Automatic Scribble Generation
- The Spatial Distribution Entropy Concept
- Scribble Searching Strategy
- Colorization Process Based on Quaternion Algebra
- Image Structure Analysis Using Quaternion Gabor Phases
- Scale-Space Contour 'Strength'
- Color Diffusion
- Experimental Results
- Conclusion
- References
- Annotation and Interactive Multimedia Applications
- Do-It-Yourself Eye Tracker: Low-Cost Pupil-Based Eye Tracker for Computer Graphics Applications
- Introduction
- Eye Tracking Technologies
- Do-It-Yourself Eye Tracker
- DIY Hardware
- ITU Gaze Tracker Software
- Evaluation of DIY Eye Tracker Accuracy
- Participants
- Hardware and Software Setup
- Stimuli and Experimental Procedure
- Results
- Application
- Conclusions and Future Work
- References
- Symbiotic Black-Box Tracker
- Introduction
- Related Work
- Symbiotic Black-Box Tracking
- The Framework
- Features for Trackers
- F2F Tracker Prediction
- T2T Propagation
- The Tracking Fusing Strategy
- Experiments
- Experiment Setting
- Parameter Tuning
- Comparison with Other Methods
- Conclusion
- References
- Identifying Objects in Images from Analyzing the Users' Gaze Movements for Provided Tags
- Introduction
- Related Work
- Experiment Design
- Analysis of Gaze Fixations on the Images
- Calculating the Precision of Tag-to-Region-Assignments
- Considered Fixation Measures
- Extending Object Boundaries and Weighting Small Objects
- Results of Finding Objects in Images
- Compare with Baselines
- Effect of Aggregation of Gaze Paths on Precision
- Results of Discriminating Objects in Images
- Conclusions
- References
- On Video Recommendation over Social Network
- Introduction
- Related Work
- Approach
- Interest Degree Estimation
- Relationship Strength Estimation
- Video Recommendation
- Experiments
- Experimental Settings
- Experimental Results
- Conclusion and Future Works
- References
- Improving Item Recommendation Based on Social Tag Ranking
- Introduction
- Recommendation Based on Tag Ranking
- Creating Tag Ranking
- Ordering Items Based on Tag Ranking
- Experiments
- Experimental Conditions
- Comparing Single Methods
- Hybrid Methods
- Effect of Co-occurrence Depth Score and Co-occurrence Width Score
- Conclusions
- References
- Event and Activity I
- Double Fusion for Multimedia Event Detection
- Introduction
- Fusion Scheme
- Implementation
- Experiment
- Data
- Evaluation
- Parameter Selection
- Results
- Conclusion
- References
- Multi-modal Solution for Unconstrained News Story Retrieval
- Introduction
- Related Work
- Enhanced Multi-modal Content Similarity
- Enhanced Textual Content Similarity
- Enhanced Visual Content Similarity
- Experimental Results
- Conclusion
- References
- Workflow Activity Monitoring Using Dynamics of Pair-Wise Qualitative Spatial Relations
- Introduction
- Related Work
- Qualitative Relations to Workflow Patterns
- Feature for Qualitative Spatial Relations
- State Space Representation of Spatial Relations
- pLSA for Modeling Spatial Relations
- Activity Monitoring
- Handling of Occlusions
- Experiments
- Evaluations
- Evaluation of Occlusions
- Conclusion
- References
- Event and Activity II
- Efficient Spatio-Temporal Edge Descriptor
- Introduction
- Previous Work
- MPEG-7 Edge Histogram Descriptor
- ST-MP7EH Spatio-Temporal Descriptor
- Experimental Setup
- ST-MP7EH Evaluation
- Comparison with Spatio-Temporal Baseline Descriptors
- Spatio-Temporal Performance Gain
- ST-MP7EH - SIFT Late Fusion
- Results
- Comparison with Spatio-Temporal Baseline Descriptors
- Spatio-Temporal Performance Gain
- ST-MP7EH - SIFT Late Fusion
- Conclusions
- References
- Recurring Element Detection in Movies
- Introduction
- Related Work
- Approach
- Region Detection
- Region Analysis and Representation
- Experiments
- Contemporary Movie
- Archived Documentaries
- Conclusion
- References
- Mining and Mobile Multimedia Applications
- Scalable Mobile-to-Mobile Video Communications Based on an Improved WZ-to-SVC Transcoder
- Introduction
- Technical Background
- WZ Coding
- Scalable Video Coding
- Related Work
- WZ to SVC Transcoding
- Motion Vectors Extraction
- Motion Vectors Mapping
- SVC Fast Encoding
- Experimental Results
- Conclusions
- References
- Place Recognition via 3D Modeling for Personal Activity Lifelog Using Wearable Camera
- Introduction
- Related Works
- Overview of the System
- Wearable Camera Setup
- Global Architecture
- 3D Scene Modeling
- 3D Reconstruction
- Annotation of the Places of Interest
- Automatic Place Detection
- 3D Localization Using Natural Landmarks
- Detection of Location Events
- Experimental Evaluation
- Dataset and Methods
- Evaluation
- Conclusion
- References
- Sensor-Based Analysis of User Generated Video for Multi-camera Video Remixing
- Introduction
- Related Work
- Automatic Video Remixing System
- Context-Sensing Client
- Automatic Video Remixing Server
- Sensor-Based Analysis
- Camera Panning Detection
- Classification of Camera Panning Based on Speed
- Identifying the Region of Interest
- Use of Panning Movements and ROI for View Switching
- Results
- Conclusions
- References
- Gait-Based Action Recognition via Accelerated Minimum Incremental Coding Length Classifier
- Introduction
- Proposed Approach
- Gait Energy Image (GEI)
- Minimum Incremental Coding Length (MICL)
- The Voting Strategy
- Experimental Results
- Input Data and Computing Environment
- Performance Evaluation
- Conclusion
- References
- Hairstyle Suggestion Using Statistical Learning
- Introduction
- Example-Based Framework
- Statistical Learning
- System Overview
- Feature Vector Design
- Hairstyle Image Synthesis
- Implementation and Evaluation
- Implementation and Result
- Evaluation
- Concluding Remarks
- References
- Search I
- Topic Based Query Suggestions for Video Search
- Introduction
- Challenges for the Video Domain
- Our Contributions
- Related Works
- Our Method
- Overall Framework
- Joint Modeling of Visual and Text
- Selecting Topics and Terms for Query Suggestions
- Experiments
- Perplexity Comparison
- Qualitative Inspection
- User Study
- Conclusion and Future Works
- References
- A Multimedia Retrieval Framework Based on Automatic Graded Relevance Judgments
- Introduction
- Related Work
- Binary Relevance Based Retrieval Systems
- A Graded Relevance Based Retrieval System
- Decision Values as Relevance Indicators
- A Multi-layer Training Set with Different Relevance Levels
- Multi-layer Prediction and Fusion
- Experimental Validation
- Binary Relevance Framework Setup: Databases and Baselines
- Graded Relevance Framework Setup: Scale Selection and Relevance Visual Results
- Results
- Conclusions and Future Work
- References
- Effective Heterogeneous Similarity Measure with Nearest Neighbors for Cross-Media Retrieval
- Introduction
- Heterogeneous Similarity Measure with Nearest Neighbors
- Learning the Ranking Model through AdaRank
- Experiments
- Dataset Description
- Contribution of Similarity Measure with Nearest Neighbors
- Contribution of Learning the Ranking Model through AdaRank
- Comparison with State-of-the-Art Methods
- Comparison with Image Retrieval System
- Conclusion
- References
- Search II
- $TempoM^2$: A Multi Feature Index Structure for Temporal Video Search
- Introduction
- Related Work
- Multi Feature Access Methods
- Access Methods for Temporal Search
- TempoM2-Index Framework
- Data Model
- TempoM2-Tree
- Search in the TempoM2-Tree
- Evaluation
- Inserting Data
- Temporal Search
- Conclusion and Future Work
- References
- Towards Automatic Detection of CBIRs Configuration
- Introduction and Background
- Related Work
- Methodology
- Approach Outline
- Feature Distribution
- Overall Process
- Approach Details
- Evaluation
- Runtime
- Feature Detection
- Weighting Allocation
- Conclusion
- References
- On Stability of Adaptive Similarity Measures for Content-Based Image Retrieval
- Introduction
- Modeling and Comparing Image Contents through Feature Signatures and Adaptive Similarity Measures
- Evaluation Measures
- Stability of a Similarity Measure
- Experimental Evaluation
- Conclusions
- References
- Retrieval of Multiple Instances of Objects in Videos
- Introduction
- DCD Representation
- Dynamic Region Construction
- Greedy Region Construction
- Simulated Annealing Optimization
- Experimental Results
- Conclusions and Perspectives
- References
- Summarization and Visualization
- Video Summarization Based on Balanced AV-MMR
- Introduction
- Review of Basic Systems
- Video-MMR
- AV-MMR
- Analysis of Audio Genres
- Analysis of Human Face
- Balanced AV-MMR
- Fundamental Balanced AV-MMR
- Balanced AV-MMR V1: Using Audio Genre
- Balanced AV-MMR V2: Using Face Detection
- Balanced AV-MMR V3: Adding Temporal Distance Factor
- The Procedure of Balanced AV-MMR
- Experimental Results
- Conclusion
- References
- Sequence Kernels for Clustering and Visualizing Near Duplicate Video Segments
- Introduction
- Kernel-Based Clustering and Visualization
- Candidate Sequence Kernels
- Kernel-Based Clustering
- Kernel-Based Visualization
- Results
- Clustering Repeated Takes
- Kernel PCA for Visualization
- Conclusion
- References
- Investigating Gesture and Pressure Interaction with a 3D Display
- Introduction
- Related Work
- Hardware
- Interfaces for Media Interaction
- Browsing Image Collections
- EPG Browsing
- User Evaluations
- System Configuration
- Collection and Tasks
- Experimental Design
- Results
- Task Performance: Image Browsing
- Task Performance: EPG Browsing
- User Preferences
- Conclusions and Discussion
- References
- Film Comic Reflecting Camera-Works
- Introduction
- Related Works
- Mapping Camera-Works from Movie to Comic
- PanelLayout
- Experimental Results
- Conclusions and Future Works
- References
- Visualization and Advanced Multimedia Systems
- Large-Scale Similarity-Based Join Processing in Multimedia Databases
- Motivation
- Multimedia Database Operations
- Related Work
- Large-Scale Processing
- Efficient Parallel Implementation
- Experimental Results
- Conclusion
- References
- Client-Driven Price Selection for Scalable Video Streaming with Advertisements
- Introduction
- Background Information
- Client-Driven Price Selection
- Performance Evaluation Methodology
- Result Presentation and Analysis
- Conclusions
- References
- Efficient Storage and Decoding of SURF Feature Points
- Introduction
- SURF Feature Points
- BelgaLogos Dataset
- Coefficient Precision
- Quantizing Coefficients
- 8 and 16-Bit Encoding
- Compression
- Evaluation
- Comparison with PCA Compression
- Conclusion
- References
- Poster Papers
- How to Select and Customize Object Recognition Approaches for an Application?
- Introduction
- Related Work
- Framework
- Task Specification
- Recognition Infrastructure and Setup
- Auto-selection and Customization
- Case Study
- Conclusions
- References
- A Fuzzy Rank-Based Late Fusion Method for Image Retrieval
- Introduction
- Fuzzy Inference Systems
- Fuzzy Rank-Based Late Fusion
- Experimental Results
- Conclusions
- References
- Annotated Free-Hand Sketches for Video Retrieval Using Object Semantics and Motion
- Introduction
- Related Work
- System Overview
- Video Feature Extraction
- Motion Segmentation and Trajectory Extraction
- Color Feature Extraction
- Semantic Labelling
- Matching the Annotated Sketch
- Motion Similarity (simM)
- Colour Similarity (simC)
- Semantic Similarity (simS)
- Experiments and Discussion
- Conclusion
- References
- Finding Suits in Images of People
- Introduction
- Visual Features for Suits Detection
- Clothing Region Location
- Color Features
- Shape Features
- Statistical Features
- Data Set and Experiments
- Data Set
- Experimental Results
- Conclusions and Future Work
- References
- The Video Face Book
- Introduction
- Multiple Face Tracking
- Face Representation and Localization
- Normalized Face Cluster Set
- Handling Multiple Faces
- Backward-Forward Tracking
- Results: Multiple Face Tracking
- Face Log Processing
- Face Clustering
- Video Index Generation
- Conclusion
- References
- Content Based Image Retrieval Using Bag-Of-Regions
- Introduction
- Bag-Of-Regions Model
- Incremental Clustering for Visual Dictionnaries
- Fusion of Multiple Retrieval Systems
- Experiments
- Incremental Clustering
- Retrieval Efficiency Using Bag-Of-Regions Vocabulary
- Combining Multiple Retrieval Systems
- Conclusion
- References
- Active Cleaning for Video Corpus Annotation
- Introduction
- Annotation Type
- Active Cleaning
- Active Learning and Cleaning Strategies, Qal and Qcl
- A Posteriori Cleaning
- Experiments
- The Active Learning Steps and the Cold-Start
- Available Annotations
- Active Cleaning Effectiveness
- A Posteriori Cleaning Effectiveness
- Conclusions
- References
- Improving Cluster Selection and Event Modeling in Unsupervised Mining for Automatic Audiovisual Video Structuring
- Introduction
- Discovering Audio-Visually Consistent Events
- Improving Cluster Selection and Event Modeling Techniques
- Estimating the Consistency of Audio-Visual Clusters
- Event Mining
- Event Modeling and Recognition
- Experimental Results
- Conclusion and Discussion
- References
- Pedestrian Attribute Analysis Using a Top-View Camera in a Public Space
- Introduction
- Detection and Tracking
- Feature Extraction from Each Frame
- Position and Area Based Features
- Shape Based Features
- Feature Extraction over the Frames
- Experimental Results
- Conclusions
- References
- A Fast GPU-Based Motion Estimation Algorithm for H.264/AVC
- Introduction
- Technical Background
- Previous Work
- Proposed GPU-Based Motion Estimation Algorithm
- Full-Pixel Motion Estimation
- Sub-pixel Accuracy Motion Estimation
- Performance Evaluation
- Metrics
- Results
- Comparison with Other Known Results
- Conclusions
- References
- A Low Complexity Macroblock Layer Rate Control Scheme Base on Weighted-Window for H.264 Encoder
- Introduction
- Brief Review of Rate Control Scheme
- Rate Control in H.264
- Proposed Weighted-Window Based Rate Control Scheme
- Weighted-Window Model
- QP Computation Model Based on Weighted-Window
- MAD Prediction Model Based on Weighted-Window
- Proposed Rate Control Framework
- Experimental Results
- Conclusion
- References
- Forward Wyner-Ziv Fast Video Decoding Using Multicore Processors
- Introduction
- Technical Background
- Distributed Video Coding
- Multicore Processor System
- Related Work
- Proposed Wyner-Ziv GOP Parallel Decoding
- Proposed Architecture
- Experimental Results
- Conclusions
- References
- Fast Mode Decision Algorithm for H.264/AVC-to-SVC Transcoding with Temporal Scalability
- Introduction
- Related Work
- Temporal Scalability in SVC
- Proposed H.264/AVC-to-SVC Video Transcoder
- Motivation
- Generating the Decision Tree
- Implementation Results
- References
- Asserting the Precise Position of 3D and Multispectral Acquisition Systems for Multisensor Registration Applied to Cultural Heritage Analysis
- Introduction
- Related Work
- Material and Methods
- Acquisition Pipeline
- Simulation Pipeline
- Acquisition Systems
- Objects under Study
- Results and Discussion
- Sarcophagus
- Wall Painting
- Conclusion and Future Work
- References
- U-Drumwave: An Interactive Performance System for Drumming
- Introduction
- U-Theatre Introduction
- Artist's Intentions and Design Strategies
- Transparent Screen
- Interaction
- Visual Content Design
- Story Intensity Curve
- System Implementations
- Physical Installation
- Virtual Projector.
- Software Architecture on the Control PC
- Audio Processing
- Onset Detection.
- Tempo Determination.
- Virtual Character
- Control Interface
- Live Demo
- Discussion
- Related Work
- Spatial Augmented Reality
- Interactive Technology for Performance
- Conclusions and Future Work
- References
- Demo Session Papers
- Real-Time Visualizations of Gigapixel Texture Data Sets Using HTML5
- Introduction
- Visualizing Gigapixel Texture Data Sets Using HTML5
- Conclusions
- References
- Enhancing the User Experience with the Sensory Effect Media Player and AmbientLib
- Introduction
- Sensory Effect Media Player and AmbientLib
- Demonstration
- References
- EMIR: A Novel Music Retrieval System for Mobile Devices Incorporating Analysis of User Emotion
- Introduction
- Approach to Emotion Detection
- Detecting Emotion from Lyrics
- User Interaction with the EMIR Demonstrator
- References
- Summarization and Presentation of Real-Life Events Using Community-Contributed Content
- Introduction
- Summarization and Presentation of Events
- Conclusion and Future Work
- References
- Tracking Persons in Ultra-HD Panoramic Video
- Introduction
- Real-Time Person Tracking
- Discussion
- References
- A Real-Time Life Experience Logging Tool
- Introduction
- A Real-Time e-Memory Prototype
- Conclusions
- References
- Video Browser Showdown
- AAU Video Browser: Non-Sequential Hierarchical Video Browsing without Content Analysis
- Introduction
- The AAU Video Browser
- Conclusion
- Reference
- Video Browser Showdown by NUS
- Introduction
- Video Browsing System
- Framework
- Visual Content-Based Search
- Text-Based Search
- Concept-Based Search
- Related Sample-Based Search
- References
- Clipboard: A Visual Search and Browsing Engine for Tablet and PC
- Introduction
- Technical Components
- Constituent Video Segmentation
- Concept Search
- Similarity Search
- Conclusion
- References
- OVIDIUS: A Web Platform for Video Browsing and Search
- Introduction
- Video Browsing
- Search Functionalities
- Video Browser Showdown Use-Case
- References
- Hierarchical Navigation and Visual Search for Video Keyframe Retrieval
- Introduction
- Hierarchical Cellular Tree
- Visual Search
- Video Browser Approach
- References
- A Key-Frame-Oriented Video Browser
- Introduction
- User Interface
- Known-Item Search in Video
- Key Frame Preprocessing
- References
- A Video Browsing Tool for Content Management in Media Post-Production
- Architecture and Workflow
- User Interface
- Reference
- Video Browsing with a 3D Thumbnail Ring Arranged by Color Similarity
- Introduction
- User Interface
- Reference
- Special Session Papers
- Interactive and Immersive Entertainment and Communication
- Multimodal Cue Detection Engine for Orchestrated Entertainment
- Introduction
- A Real-Time Architecture
- Multiple Face Tracking
- Multiple Person Identification
- Head Pose Estimation
- Visual Focus of Attention
- Direction of Arrival Estimation
- Voice Activity Detection
- Keyword Spotting
- Improvements and Results
- Conclusion
- References
- The Ultimate Immersive Experience: Panoramic 3D Video Acquisition
- Introduction
- Review of Omni-Directional Imaging and Panoramic 2D Video
- Extension to Omni-Stereo Imaging and Panoramic 3D Video
- Experimental Results and Proof-of-Concept
- Conclusion
- References
- The FascinatE Production Scripting Engine
- Introduction
- Related Work
- Scenarios and Features
- The FascinatE System
- AV Content Analysis
- EditorUI Tools
- Delivery Scripting Engine (DSE)
- The Production Scripting Engine
- Semantic Lifting
- Shot Candidate Identification
- Shot Framing
- Shot Prioritization and Shot Selection
- Discussion
- References
- Multimedia Preservation: How to Ensure Multimedia Access over Time?
- Linking User Generated Video Annotations to the Web of Data
- Introduction
- Waisda? Video Labelling Game
- Related Work
- Linking Video Annotations to Concepts
- Reconciliation API
- Linked Open Data Sources
- User Interface
- User Experiment
- Setup
- Results
- Lessons Learned
- Discussion
- References
- Challenges in Storing Multimedia Data for the Future - An Overview
- Introduction
- Related Work
- Hardware
- Magnetic Media
- Optical Media
- Software and Encoding
- Organization and Finding of Contents
- Security and Privacy Concerns
- Conclusion
- References
- Multi-modal and Cross-modal Search
- Optimizing Multimedia Retrieval Using Multimodal Fusion and Relevance Feedback Techniques
- Introduction
- Creating a Multimodal Feature Space
- Basic Concepts and Overview
- Multimodal Feature Space Creation
- An Indexing Scheme for Large-Scale Multimodal Retrieval
- Improving Retrieval Using Relevance Feedback
- Relevance Feedback Methods
- Experimental Results
- Conclusions
- References
- Context-Aware Querying for Multimodal Search Engines
- Introduction
- Related Work
- Methodology
- Multimodal Query Interfaces - MuSeBag
- Multimodal Interaction Handling - UIIFace
- Collaborative Search - CoFind
- Implementation Details
- CSS3 Media Queries
- Canvas
- HTML5 Audio and Video
- File API
- Geolocation
- Sensors
- Device API
- Evaluation
- Conclusion and Future Work
- References
- A Novel Multi-modal Integration and Propagation Model for Cross-Media Information Retrieval
- Introduction
- Correlation Learning
- Multi-modal Gaussian PLSA
- Multi-modal Learning
- Correlation Propagation
- Experiments and Discussions
- Conclusion
- References
- Video Surveillance
- RGB-D Based Multi-attribute People Searchin Intelligent Visual Surveillance
- Introduction
- System Overview
- RGB-D Camera
- Attributes Extraction
- Data Storage and User Search Interface
- Attributes Extraction
- Human Segmentation
- Details of Attributes Extraction
- Experimental Results
- Performance of Attributes Extraction
- Evaluation of Multi-attribute People Searching
- Conclusions and Future Work
- References
- Template Matching and Monte Carlo Markova Chain for People Counting under Occlusions
- Introduction
- Pedestrian Detection under Occlusions
- Bayesian Estimation
- Estimation through Markov Chain Monte Carlo
- Head-Shoulder Hypothesis Generation
- Head Detection from Multiple Templates
- Head-ShoulderO model
- Head Symmetry
- Histogram of Gradients on Polar Coordinate
- LDA-Based Object Detection
- Experimental Results
- References
- Visual-Based Spatiotemporal Analysis for Nighttime Vehicle Braking Event Detection
- Introduction
- Brake Lights Detection
- Preprocessing - Contrast Enhancement
- Modeling Tail Lights by Nakagami Distribution
- Adaptive Decision Making for Brake Light Detection
- Experimental Results
- Conclusions
- References
- Fusing Template and Point Information to Track Planes with Large Interframe Displacement
- Introduction
- Fusing Point and Template Information
- Results and Discussion
- Conclusion
- References
- Author Index
