Advances in Multimedia Information Processing - PCM 2009

Welcome to the proceedings of the 10th Pacific Rim Conference on Multimedia (PCM 2009) held in Bangkok, Thailand, December 15-18, 2009. Since its inception in 2000, PCM has rapidly grown into a major conference on multimedia in the Asia- Pacific Rim region and has built up its reputation around the world. Following the success of the preceding conferences, PCM 2008 in Taiwan, PCM 2007 in Hong Kong, PCM 2006 in China, PCM 2005 in Korea, PCM 2004 in Japan, PCM 2003 in Singapore, PCM 2002 in Taiwan, PCM 2001 in China, and PCM 2000 in Australia, the tenth PCM brought researchers, developers, practitioners, and educators together to disseminate their new discoveries in the field of multimedia. Theoretical bre- throughs and practical systems were presented at this conference, thanks to the s- port of Naresuan University, Mahanakorn University of Technology, and the IEEE Thailand Section. PCM 2009 featured a comprehensive program including keynote talks, regular - per presentations, posters, and special sessions. We received 171 papers from 16 countries including Australia, Sweden, German, Italy, Iran, France, Canada, China, Japan, Korea, Malaysia, Singapore, Taiwan, Hong Kong, the UK, and the USA. After a rigorous review process, we accepted only 67 oral presentations and 45 poster pr- entations. Four special sessions were also organized by world-leading researchers.

Welcome to the proceedings of the 10th Pacific Rim Conference on Multimedia (PCM 2009) held in Bangkok, Thailand, December 15-18, 2009. Since its inception in 2000, PCM has rapidly grown into a major conference on multimedia in the Asia- Pacific Rim region and has built up its reputation around the world. Following the success of the preceding conferences, PCM 2008 in Taiwan, PCM 2007 in Hong Kong, PCM 2006 in China, PCM 2005 in Korea, PCM 2004 in Japan, PCM 2003 in Singapore, PCM 2002 in Taiwan, PCM 2001 in China, and PCM 2000 in Australia, the tenth PCM brought researchers, developers, practitioners, and educators together to disseminate their new discoveries in the field of multimedia. Theoretical bre- throughs and practical systems were presented at this conference, thanks to the s- port of Naresuan University, Mahanakorn University of Technology, and the IEEE Thailand Section. PCM 2009 featured a comprehensive program including keynote talks, regular - per presentations, posters, and special sessions. We received 171 papers from 16 countries including Australia, Sweden, German, Italy, Iran, France, Canada, China, Japan, Korea, Malaysia, Singapore, Taiwan, Hong Kong, the UK, and the USA. After a rigorous review process, we accepted only 67 oral presentations and 45 poster pr- entations. Four special sessions were also organized by world-leading researchers.

Welcome to the proceedings of the 10th Pacific Rim Conference on Multimedia (PCM 2009) held in Bangkok, Thailand, December 15-18, 2009. Since its inception in 2000, PCM has rapidly grown into a major conference on multimedia in the Asia- Pacific Rim region and has built up its reputation around the world. Following the success of the preceding conferences, PCM 2008 in Taiwan, PCM 2007 in Hong Kong, PCM 2006 in China, PCM 2005 in Korea, PCM 2004 in Japan, PCM 2003 in Singapore, PCM 2002 in Taiwan, PCM 2001 in China, and PCM 2000 in Australia, the tenth PCM brought researchers, developers, practitioners, and educators together to disseminate their new discoveries in the field of multimedia. Theoretical bre- throughs and practical systems were presented at this conference, thanks to the s- port of Naresuan University, Mahanakorn University of Technology, and the IEEE Thailand Section. PCM 2009 featured a comprehensive program including keynote talks, regular - per presentations, posters, and special sessions. We received 171 papers from 16 countries including Australia, Sweden, German, Italy, Iran, France, Canada, China, Japan, Korea, Malaysia, Singapore, Taiwan, Hong Kong, the UK, and the USA. After a rigorous review process, we accepted only 67 oral presentations and 45 poster pr- entations. Four special sessions were also organized by world-leading researchers.

Keynote Paper.- Kernel Approaches to Unsupervised and Supervised Machine Learning.- Special Session 1: Exploring Large-Scale Videos: Automatic Content Genre Classification, Repair, Enhancement, and Authentication.- Separation of Professional and Amateur Video in Large Video Collections.- Intensity Flicker Removal in Digitized Old Films Using Global-Local Histogram Transform.- Transmission Rate Enhancement for Scalable H.264/AVC Video over MIMO Wireless Systems.- On Peer Selection and Protection for Reliable Peer-to-Peer Video Streaming.- An Efficient Upsampling Technique for Images and Videos.- Session 1: Human Behavior Classification and Recognition.- Metric Learning for Regression Problems and Human Age Estimation.- Spatiotemporal Phase Congruency Based Invariant Features for Human Behavior Classification.- An Innovative Weighted 2DLDA Approach for Face Recognition.- 3D Human Body Tracking in Unconstrained Scenes.- Transfer Discriminative Logmaps.- Session 2: Art.- A Movement Data Analysis and Synthesis Tool for Museum Visitors’ Behaviors.- Photo Vignetting and Camera Orientation Correction for High Precision Acquisition.- Chinese Calligraphy Character Image Synthesis Based on Retrieval.- Stereoscopic Video Conversion of 2D Painting for Tour-Into-Picture.- Special Session 2: Image and Video Coding towards Perceptual Quality Improvement.- Improving Intra Coding in H.264AVC by Image Epitome.- Image Quality Assessment Using Spatial Frequency Component.- Perception Based Down Sampling for Low Bit Rate Image Coding.- Adaptive DCT-Domain Down-Sampling and Learning Based Mapping for Low Bit-Rate Image Compression.- A Learning-Based Framework for Low Bit-Rate Image and Video Coding.- Session 3: Image Annotation, Retrieval, and Classification.- Generalized Relevance Models for Automatic Image Annotation.- Sorting Holiday Photos without a GPS: What Can We Expect from Contents-Based Geo-spatial Image Tagging?.- Detecting “In-Play” Photos in Sports News Photo Database.- Structural Context for Object Categorization.- Saliency Regions for 3D Mesh Abstraction.- Session 4: Application.- Probability Based Page Data Allocation Scheme in Flash Memory.- Robust Alignment of Presentation Videos with Slides.- Forecasting KOSPI Using a Neural Network with Weighted Fuzzy Membership Functions and Technical Indicators.- A Sound-Directed Cameraman Accommodating Unfettered-Speaking in e-Learning Classrooms.- Determination of Golf Ball Flight Based on Planar Structure Sensor.- A Novel Macro-Block Group Based AVS Coding Scheme for Many-Core Processor.- Session 5: Object Detection and Tracking.- Automatic Detection of Object of Interest and Tracking in Active Video.- Human Pose Tracking Using Motion-Based Search.- Robust Object Tracking Using Particle Filters and Multi-region Mean Shift.- A Quick Filtering for Similarity Queries in Motion Capture Databases.- Session 6: Networking Technologies.- Optimization of Multicast Routing Based on a Reliable Effective Framework in Wireless Mesh Networks.- QoS Aware Layered Multi-Cast with Network Coding in Lossy Networks.- A Classified P2P Overlay Scheme Using SVC for Video Streaming.- Broadcast Encryption-Based P2P DRM without Central License Server.- Session 7: Audio Processing and Applications.- Rhythm Speech Lyrics Input for MIDI-Based Singing Voice Synthesis.- Design of Wireless Sensor Networks with Filtering Duplicate Audio Signals.- A Neural Network Based Framework for Audio Scene Analysis in Audio Sensor Networks.- A Robust Audio Content Protection Scheme.- Special Session 3: 3DTV and Multi-view Video.- Dense Depth Map Acquisition System for 3DTV Applications Based on Active Stereo and Structured Light Integration.- Linear Prediction for Interactivity of Multiview Video Application.- Non-linear Bi-directional Prediction for Depth Coding.- Spatio-temporally Consistent Multi-view Video Synthesis for Autostereoscopic Displays.- Virtual View Interpolation and Prediction Structure for Full Parallax Multi-view Video.- A Gradient-Based Adaptive Interpolation Filter for Multiple View Synthesis.- Session 8: Image Watermarking.- Robust Watermarking in DoG Scale Space Using a Multi-scale JND Model.- Performance Comparison of Digital Watermarking for Scanned Document in RGB and YC b C r Channels.- Robust Block and Gray-Level Histogram Based Watermarking Scheme.- Improved Digital Watermarking Using DWT Masking.- A Reversible Watermarking Scheme for High-Fidelity Applications.- RST-Invariant Semi-fragile Image Authentication Based on DWT-Coefficient Quantization.- Session 9: Multimedia Document Search and Retrieval.- Multi-modal Correlation Modeling and Ranking for Retrieval.- Learning to Retrieve Opinions.- Adaptive Learning for Multimodal Fusion in Video Search.- Intelligent Music Playlist Recommendation Based on User Daily Behavior and Music Content.- A Hierarchical Semantics-Matching Approach for Sports Video Annotation.- Special Session 4: Intelligent Multimedia Security and Forensics (I).- Digital Image Splicing Using Edges.- Improving a Digital Rights Management Scheme for Video Broadcast.- Palmprint Recognition Based on Subspace Analysis of Gabor Filter Bank.- Block Based Video Data Hiding Using Repeat Accumulate Codes and Forbidden Zone Data Hiding.- Protection of DRM Agent Codes.- Session 10: Multimedia Content Management.- News Topic Tracking and Re-ranking with Query Expansion Based on Near-Duplicate Detection.- An Effective Audio-Visual Information Based Framework for Extracting Highlights in Basketball Games.- A Novel Retake Detection Using LCS and SIFT Algorithm.- Video Shrinking by Auditory and Visual Cues.- DCT-Based Videoprinting on Saliency-Consistent Regions for Detecting Video Copies with Text Insertion.- Session 11: Image Analysis and Matching.- Efficient NCC-Based Image Matching Based on Novel Hierarchical Bounds.- Copy-Move Forgery Detection in Digital Image.- Extraction of 2D Barcode Using Keypoint Selection and Line Detection.- Influence of the Smooth Region on the Structural Similarity Index.- Structure-Preserving Colorization Based on Quaternionic Phase Reconstruction.- Special Session 4: Intelligent Multimedia Security and Forensics (II).- Image Splicing Detection Using Multi-resolution Histogram.- Toward Quality Improvement in Location Map Free Reversible Watermarking.- Motion Consideration in H.264/AVC Compressed Video Watermarking.- Spatio-temporal Just Noticeable Distortion Model Guided Video Watermarking.- Crowd Flow Segmentation Using a Novel Region Growing Scheme.- Surveillance Audio Attention Model Based on Spatial Audio Cues.- Poster Session 1: Multimedia Analysis and Retrieval.- A Novel Role-Based Movie Scene Segmentation Method.- Soccer Video Shot Classification Based on Color Characterization Using Dominant Sets Clustering.- Weakly-Supervised Violence Detection in Movies with Audio and Video Based Co-training.- Concept-Specific Visual Vocabulary Construction for Object Categorization.- Reducing Manual Feedback in a Distributed CBIR System.- Fast Computation of Similarity Based on Jaccard Coefficient for Composition-Based Image Retrieval.- Clustering of Retrieved Images by Integrating Perceptual Signal Features within Keyword-Based Image Search Engines.- A Graph Based Approach to Speaker Retrieval in Talk  Show Videos with Transcript-Based Supervision.- Poster Session 2: Advanced Image and Video Processing Techniques.- Anti-shaking Algorithm for the Mobile Phone Camera in Dim Light Conditions.- Universal Capture through Stereographic Multi-perspective Recording and Scene Reconstruction.- A Class of Non-redundant Directional Filter Banks.- A Novel Approach for Bayesian Image Denoising Using a SGLI Prior.- Digital Image Forensics Using EM Algorithm.- Minimizing Video Data Using Looping Background Detection Technique.- Extracting Key Frames for Surveillance Video Based on Color Spatial Distribution Histograms.- Color Space Transformation from RGB to CIELAB Using Neural Networks.- Session 12: Coding.- MPEG-2 to H.264/AVC Intra Frame Transcoding.- Multichannel Correlation Model for Efficient Decoding in Wyner-Ziv Video Codec.- Motion Vector Coding Based on Optimal Predictor Selection.- Block Adaptive Super Resolution Video Coding.- An Efficient MB Layer Rate Control for H.264/AVC Based on Adaptive QP Decision.- Reducing the Motion-Compensated Temporal Interpolation Noise of DVC Side Information by ODWT.- Poster Session 3: Multimedia Systems and Applications.- Persian Viseme Classification for Developing Visual Speech Training Application.- CampusGenie – A Campus-Life Assistant on the Mobile-Phone.- Context Aware and Content Adaptation of Template Based Multimedia Presentation on Handset Devices.- Normalized Cut Based Coherence Measure Construction for Scene Segmentation.- Edge-Based Algorithm for Shadows and Ghosts Removing.- Immersive Mixed Media Augmented Reality Applications and Technology.- BTS Information Signs Analysis Based on Image Compression and Classification for Virtual Blind Man Multimedia Guidance System.- Evaluating a Multimedia-Based Tele-Ophthalmology System.- Cost-Effective Wiimote-Based Technology-Enhanced Teaching and Learning Platform.- Poster Session 4: Multimedia Communication and Networking.- A Novel Priority Classification Scheme for Packet Video over DiffServ Networks.- Nodes Placement for Optimizing Coverage of Visual Sensor Networks.- Opportunistic Contention-Based Feedback Protocol for Downlink OFDMA Systems with Mixed Traffic.- Audio-Visual Information Clues about Geographic Data on Mobile Interfaces.- The Methods for Temporal Scalable Extension of AVS Video.- Enhancing Video Quality over IEEE 802.11e WLAN Using Cross Layer Design.- Session 13: Advanced Image Processing Techniques.- Fast and Effective Interpolation Using Median Filter.- A New Free Reference Image Quality Index Based on Perceptual Blur Estimation.- Nonlocal Edge-Directed Interpolation.- Adaptive Block-Size Transform Based Just-Noticeable Difference Profile for Images.- Exploiting a Growing Self-organizing Map for Adaptive and Efficient Color Quantization.- Poster Session 5: Multimedia Compression and Optimization.- Photorealistic Geometry Image Coding Based on Directional Lifting Wavelet Transform.- Power Scalable Video Encoding Strategy Based on Game Theory.- An Adaptive Multiple Reference Frame Motion Estimation for H.264 Video Coding.- Quality Improvement of Compressed Color Images by Model-Based Chrominance Estimation.- A Novel Multiple-Description Image Coding on Wavelet.- Encoding Time Reduction for the Enhancement Layer in the H.264/AVC Extension-Spatial SVC.- Video Quality Comparison of H.264/AVC and AVS in High Fidelity Profiles.- A Synthetic Region Selection Strategy for Texture Synthesis Based Video Coding.- Poster Session 6: Multimedia Security Rights and Management.- Multi-watermarking Scheme for Copyright Protection and Content Authentication of Digital Audio.- A High Capacity Reversible Watermarking Scheme Based on an Integer Transform.- Pixel-Wise Based Digital Watermarking in YC b C r Color Space.- Reversible Watermarking Based on Statistical Quantity Histogram.- A Novel Differential Energy Watermarking Scheme Based on FSM Model against Video Time-Space Tampering.- Secure Domain Architecture for Interoperable Content Distribution.