Advances in Multimedia Information Processing -- PCM 2010, Part II : 11th Pacific Rim Conference on Multimedia, Shanghai, China, September 21-24, 2010 Proceedings

Cover......Page 1 Lecture Notes in Computer Science 6298......Page 2 Advances in Multimedia Information Processing -- PCM 2010, Part II: 11th Pacific Rim Conference on Multimedia, Shanghai, China, September 21-24, 2010 Proceedings......Page 3 Preface......Page 5 Table of Contents – Part II......Page 10 Table of Contents – Part I......Page 16 Introduction......Page 22 Principal Components Analysis......Page 23 Nonlinear Methods for Dimensionality Reduction......Page 24 Low-Level Features Extraction......Page 25 Feature Reduction Using CUR Matrix Decomposition......Page 26 The Compact Feature Representation by Auto-encoder......Page 27 Experimental Setup......Page 29 Comparison of Different Dimensionality Reduction Methods......Page 30 Experiment Using Auto-encoder with Different Depth......Page 31 Reference......Page 32 Introduction......Page 34 Query Formulation......Page 36 Scalability Improvement - Indexing Structure Design for Fast Search......Page 38 Recommendation Systems......Page 39 Conclusion......Page 40 References......Page 41 Related Work......Page 43 Notation......Page 44 Sparse Logistic Regression......Page 45 Sparse Logistic Regression for Correlation Learning......Page 46 Evaluation Metrics......Page 48 References......Page 50 Introduction......Page 52 Related Work......Page 53 Problem Definition......Page 54 SMS......Page 56 Photograph......Page 58 Heterogeneous PLL Objects Clustering......Page 59 Activity Theme Relevancy Measurement......Page 60 The Project Kaleido Photo – A Prototype of Mobile PLL Objects Organization System......Page 61 References......Page 62 Introduction......Page 64 Overview......Page 65 Video Segmentation by Script Partition......Page 66 Affective Script Partition Analysis......Page 67 Affective Feature Extraction......Page 69 Experiments......Page 70 References......Page 71 Introduction......Page 73 Partition Based Storage Format......Page 75 DPCM-Based Variable Length Coding......Page 76 Joint Coding for Co-located and Last-line Data......Page 77 Whole Architecture......Page 79 Implementation Results......Page 80 References......Page 81 Introduction......Page 83 Architecture of AVS Video Encoder and Mode Decision......Page 84 Original Algorithm: All Modes Enabled Algorithm......Page 86 Optimal Algorithm: Mode Pre-selection Algorithm......Page 87 First Step: 4-Way Parallel Scanning for Run, Level and VLC Table......Page 88 Second Step: Connection and VLC Table Fix......Page 90 Coding Performance Comparison......Page 91 Simulation and Resources Evaluation......Page 92 References......Page 93 Introduction......Page 94 Time Complexity......Page 95 Empirical Analysis on RDC......Page 97 AVS Encoding RDP Experiments......Page 100 References......Page 103 Introduction......Page 105 Research Background......Page 106 Encoding Framework......Page 108 Temporal Sampling......Page 110 I-Frame Coding: Vector Quantization......Page 111 B-Frame Coding: Interpolation and Residual Coding......Page 114 Experimental Results......Page 116 Statistics of CMU Mocap Data......Page 117 Performance Evaluation......Page 118 Conclusion and Future Work......Page 119 References......Page 120 Introduction......Page 121 The Framework of our Algorithm......Page 122 Textural-Classification-Based Coding......Page 124 Experiment and Discussion......Page 125 References......Page 130 Introduction......Page 132 Searching for Candidates......Page 135 Adaptive Transform......Page 137 Experiments......Page 138 Conclusion......Page 140 References......Page 141 Introduction......Page 142 Overview of the Mode Decision Process in SVC......Page 143 Overview of Spatiograms......Page 146 Study of Mode Distribution between H.264 Modes......Page 147 Study of Similarity Score against SVC Only Modes......Page 148 Computation of Adaptive Threshold for Various Mode Categories......Page 149 New Algorithm for SVC Inter Layer Prediction Modes......Page 150 Experiments and Results......Page 151 Results for Experiment 1......Page 152 Results of Experiment 2......Page 153 References......Page 154 Appendix 1......Page 156 Introduction......Page 157 Overview of Mode Decision in H.264 Scalable Video Coding......Page 158 MB Classification and Check......Page 159 Fast Intra Mode Selection Algorithm......Page 161 Experimental Results......Page 162 References......Page 164 Introduction......Page 166 Mode Classification Based on RD Cost Characteristics......Page 167 Early Skip Mode Detection......Page 169 Best Non-skip Mode Decision......Page 171 Experimental Results......Page 172 Conclusions......Page 175 References......Page 176 Introduction......Page 177 Multi-pass VBR Rate Control Algorithm......Page 178 First and Second Pass Encodings......Page 179 The Third Pass Encoding......Page 183 Experimental Results......Page 184 References......Page 186 Introduction......Page 188 Global Nonlinear Algorithms......Page 190 Sparsity Reconstruction Embedding......Page 191 Sparse Reconstruction......Page 192 Explanation and Analysis......Page 193 Experiment Setup......Page 195 Experiment Results......Page 197 Conclusion......Page 198 References......Page 199 Introduction......Page 200 Statistical Learning Approaches......Page 202 Feature Selection......Page 203 Training and Off-Line Pre-classification......Page 204 Proposed Statistical Learning Based H.264 Encoder......Page 205 Experimental Results......Page 206 References......Page 209 Introduction......Page 211 Spatial Scalable Video Coder Structure......Page 212 Rate and Distortion Models in SAQD-Domain......Page 213 Optimum Bit Allocation......Page 216 Quantization Step Determination......Page 218 Experimental Results and Analysis......Page 219 References......Page 220 Appendix A......Page 221 Appendix B......Page 222 Introduction......Page 223 3-D Pyramid Decomposition......Page 225 Spatio-temporal CSF......Page 226 Contrast Masking......Page 228 Saliency Masking......Page 229 Experimental Results......Page 230 References......Page 233 Introduction......Page 235 Framework Overview......Page 237 Point Set Denoising......Page 238 Resolution and Initial Parameter Estimation......Page 239 Gaussian Kernel and Convolution......Page 240 Subsampling Method......Page 241 Experimental Results and Analysis......Page 242 Experimental Results for Decimation......Page 243 References......Page 245 Introduction......Page 247 Wavelet-Based Eigentransformation......Page 248 Experiments......Page 251 References......Page 255 Introduction......Page 256 Spatial Scalability......Page 257 Real-Time Architecture for Inter-layer Prediction of H.264/SVC......Page 259 ILIP-UP Architecture......Page 260 ILRP-UP Architecture......Page 261 Simulation Results......Page 262 References......Page 264 Introduction......Page 266 DCT Domain Downsizing......Page 267 Implementation......Page 269 Experimental Results......Page 270 References......Page 271 Introduction......Page 273 Inter/Intra Mode Decision for H.264/AVC......Page 274 Statistical Analysis of H.264/AVC Downscaled Videos......Page 275 Efficient Inter/Intra Mode Decision for H.264/AVC Downscaled Videos......Page 277 Experimental Results......Page 280 Experimental Results......Page 283 References......Page 284 Introduction and Related Work......Page 285 The MB Classification Method......Page 286 Insight of MB Class Information in Shot Change Detection......Page 288 The Class-Based Shot Change Detection Algorithm......Page 289 Experimental Results......Page 290 Discussion and Extension......Page 293 Conclusion......Page 295 References......Page 296 Introduction......Page 297 Optimization on the Flow of Choosing Modes......Page 298 Optimization on Pixel Search Algorithm......Page 299 Implementation and Optimization based on DSP......Page 302 Performance......Page 303 References......Page 305 Introduction......Page 306 System Architecture......Page 307 Difference Detection Flow......Page 308 Implementation Complexity Analysis......Page 310 Encoder Adaptability......Page 311 Testing Conditions......Page 312 Testing Results......Page 314 References......Page 317 Introduction......Page 318 The Temporal Scalable Decoding Process Flow and System Architecture......Page 319 The Proposed Method in the P Frame-Skipping Process......Page 321 Experimental Result......Page 326 Conclusion......Page 328 References......Page 329 Introduction......Page 330 Layered Block Matching Super-Resolution......Page 331 Video Coding With LBM-SR......Page 333 The Performance of LBM-SR......Page 335 References......Page 339 Introduction......Page 340 Proposed Sampling-Aided MVC Scheme......Page 341 Merging and Detaching the Sampled Views......Page 342 Experimental Results......Page 343 References......Page 347 Introduction......Page 349 The Structure of the Proposed WZ-to-AVS Transcoder......Page 351 Side Information Generation......Page 352 Transcoding Strategy......Page 354 Rate-Distortion Performance......Page 356 Complexity Analysis......Page 358 References......Page 359 Introduction......Page 361 Motion Vector Coding......Page 362 Motion Vector Competition......Page 363 Distribution of Motion Vector Predictor......Page 365 Motion Vector Predictor Index Coding Using Phased-in Code......Page 366 Experimental Results and Analysis......Page 368 References......Page 370 Introduction......Page 371 Related Work......Page 372 The Proposed Method......Page 373 Image Segmentation......Page 374 Cost Function for Transmission Map Estimation......Page 375 Refinement of Transmission Map Using Soft Matting......Page 377 Recovering the Scene Radiance......Page 378 Experimental Results......Page 379 References......Page 381 Introduction......Page 383 Overview of the Anisotropic Diffusion......Page 384 Method Noise of Anisotropic Diffusion......Page 385 Anisotropic Diffusion Using the Non-local Algorithm......Page 386 Experimental Results......Page 389 References......Page 391 Introduction......Page 393 Redundant Macro-Block Texture-based Selective Boundary Matching Algorithm......Page 394 RMB Coding......Page 395 TSBMA......Page 397 Experiment Results......Page 399 Conclusion......Page 401 References......Page 402 Introduction......Page 403 System Description......Page 404 R-D Curve of Input Image with System Constraints......Page 405 Features of Optimal Solutions......Page 406 Relations of System Parameters, Optimization Objective, and System Constraints......Page 408 Description of Optimization Algorithm......Page 410 Algorithm Effectiveness......Page 411 Computational Complexity......Page 412 Reference......Page 413 Introduction......Page 415 Motion Vector Extrapolation with MV Candidate List......Page 417 Tentative Projection with Pixel-MV Distortion Estimation......Page 418 Bi-direction MV Retrieval Based Extension......Page 421 MV Selection......Page 422 Experimental Results......Page 423 References......Page 425 Introduction......Page 426 Related Work......Page 427 Sender Side......Page 429 Receiver Side......Page 433 Evaluation......Page 434 Discussion......Page 436 References......Page 437 Introduction......Page 439 Impact of $ igma_{R}$ for Packet Delay Performance and Transmission Distortion......Page 440 Multi-Hop Packet Delay Bound Violation Modeling......Page 441 Problem Description......Page 443 Construction of R-D Profile......Page 444 Performance Evaluation of the Proposed Model......Page 446 Performance Evaluation of Low-Pass R-D Control......Page 447 Conclusion......Page 449 References......Page 450 Introduction......Page 451 Edge-weighted Adaptive Filtering (EWAF)......Page 452 Edge Modified Based Image Zooming......Page 455 Subjective Visual Evaluation......Page 457 Conclusions......Page 458 References......Page 459 Introduction......Page 460 HMM Based Soccer Video Events Detection Approach......Page 461 Middle Level Semantics Classification......Page 462 Video Text Type Classification......Page 463 Event Boundary Detection and Observations Extraction......Page 464 Event Detection Using Enhanced HMMs......Page 465 Experimental Results and Discussions......Page 466 Event Detection Performance Evaluation......Page 467 Discussions on the Selection of Overall Observations and Hidden States......Page 469 References......Page 470 Introduction......Page 473 Alternate Flashing System......Page 474 Synthesis of Unlit Frames......Page 475 Combining Lit and Unlit Frames......Page 477 Object Segmentation......Page 478 Conclusions......Page 481 References......Page 482 Introduction......Page 483 Motion Attention Detection......Page 484 Static Attention Detection......Page 485 Visual Attention Region Detection......Page 486 Object Motion Trajectory Tracking......Page 487 Experiments......Page 488 Conclusion......Page 490 References......Page 491 Introduction......Page 492 Related Studies......Page 493 Human-Computer Collaboration Model......Page 494 Recognition Improvement Framework......Page 495 Information Feedback Algorithm......Page 496 System Overview......Page 497 (I) Recognition Algorithm......Page 498 (II) Detection of Unfavorable Situation......Page 499 Configurations......Page 500 Results and Discussions......Page 501 References......Page 503 Introduction......Page 504 The Proposed Tracking Algorithm......Page 506 Training Phase......Page 507 Tracking Phase......Page 509 Experiments......Page 510 Conclusion and Discussion......Page 513 References......Page 514 Introduction......Page 515 Related Work......Page 516 LDA-Based Method......Page 517 Gibbs Sampling for LDA......Page 518 Soft-Constraint Based LDA......Page 519 Online LDA......Page 521 Recommendation Quality......Page 522 Efficiency of Online System......Page 524 References......Page 525 Introduction......Page 527 Degraded Chinese Character Recognition......Page 529 Coarse Classification Based on K-Nearest Neighbor Classifier......Page 530 Fine Classification via Sparse Representation......Page 531 Evaluation on Low Resolution Images......Page 532 References......Page 534 Introduction......Page 536 Related Work and Proposed System......Page 537 Extracting Visual Features......Page 538 Graphical User Interface......Page 541 Experiments and Results......Page 544 Conclusions......Page 545 References......Page 546 Introduction......Page 547 The Shape Model......Page 548 The Proposed Method......Page 549 The First Stage......Page 550 The Second Stage......Page 554 Experimental Results......Page 555 Conclusion......Page 557 References......Page 558 Introduction......Page 559 Proposed Method......Page 560 Identifying the Active Joint Dimensions......Page 561 Calculating the Un-correlation Measure......Page 562 Computing the Non-smoothness Measure......Page 563 Experiments......Page 564 Conclusion and Future Work......Page 568 References......Page 569 Introduction......Page 570 Materials and Methods......Page 571 Experimental Results......Page 572 Conclusions......Page 578 References......Page 579 Introduction......Page 580 Collaborative Filtering......Page 581 Tag-Boosted CF via Tripartite Graph Random Walk......Page 582 Tag Expansion via Lasso Logistic Regression......Page 584 Tag Incorporation via Weighting Parameter......Page 585 Dataset......Page 586 Effects of Tag-Boosted CF......Page 587 Effects of Tag Expansion......Page 588 Reference......Page 590 Introduction......Page 592 Related Work......Page 593 Problem Statement and Our Facing Aging Model......Page 594 Geometric Affine Transformation for Face Warping......Page 595 Motion Vector Deduction......Page 596 Aging Skin Texture Synthesis by Sparse Representation......Page 597 Sparse Representation of Aging Face......Page 598 Aging Parameters Learning......Page 599 Aging Texture Synthesis Based on MRF......Page 600 Conclusion and Future Work......Page 601 References......Page 602 Introduction......Page 604 The Multimodal Interaction Paradigm......Page 606 Grouping Methods......Page 608 Scenario......Page 610 The System Network......Page 611 The Client......Page 613 References......Page 614 Introduction......Page 616 Goal of the Proposed MOs Detection......Page 617 Motion JPEG......Page 618 DCT-SPC......Page 619 Algorithm......Page 620 MOs Detection in Codestream Domain......Page 621 More Robust Detection......Page 622 Experimental Results......Page 623 Robust Detection Using Multiple DCT Blocks......Page 624 References......Page 627 Introduction......Page 628 Zero-Block Mode Decision for H.264/AVC......Page 629 Computation of Number of Zero-Blocks Using Prediction Motion Vectors......Page 631 Experimental Results......Page 634 References......Page 636 Introduction......Page 638 Curvelet Transform......Page 639 Facial Feature Point Selection......Page 640 Curvelet Subband Entropy......Page 641 Experiments and Results......Page 643 Experiments without Cross-Validation......Page 644 Experiments with Cross-Validation......Page 645 Conclusion and Scope for Future Work......Page 646 References......Page 649 Introduction......Page 650 The Limitation of Traditional Technique......Page 651 The Definition of Video Structured Description......Page 652 The Key Aspects of Video Structure Description......Page 653 Compared VSD with Traditional IVS......Page 654 Introduction of a Prototype System......Page 655 Discussion......Page 656 References......Page 657 Introduction......Page 658 CVD Color Space......Page 660 Key Color Remapping......Page 662 Experimental Results......Page 665 References......Page 667 Introduction......Page 669 Video Segmentation......Page 670 Text Localization......Page 671 Text Extraction......Page 673 Structure of the Arabic Scripts......Page 674 Pre-Processing......Page 675 Script Segmentation......Page 676 Classification......Page 677 Experimental Results......Page 678 References......Page 679 Introduction......Page 681 Related Research......Page 682 Moving Objects Detection......Page 683 Y-axis Offset Calculation......Page 685 Correction of X-axis Perspective Distortions......Page 687 Video Contents Integration......Page 688 Experiments and Discussions......Page 690 References......Page 691 Introduction......Page 693 Related Works......Page 694 Select Candidates for Facial Features......Page 696 Pairwise Facial Features......Page 697 Experimental Results......Page 698 Conclusions......Page 701 References......Page 702 Introduction......Page 703 Model-Based HRTF......Page 705 Image Method Based Reverberation......Page 706 Spectral Notch Filtering......Page 708 Proposed Sound Externalization Method......Page 709 Performance Evaluation......Page 711 References......Page 713 Introduction......Page 715 The Fractional Fourier Transform And The Two Dimensions Fractional Fourier Transform......Page 716 Facial Data Acquisition And Visual Feature Extraction......Page 718 Emotional State Classification And Premilinary Result......Page 720 References......Page 724 Introduction......Page 726 Related Work and Methodology......Page 728 Patient’s Component......Page 730 References......Page 734 Introduction......Page 737 Related Work......Page 738 Motion Coherence Based Spatiotemporal Interest Point Detector......Page 739 Gradient Based Descriptor......Page 741 Kernels......Page 742 Implementation......Page 743 Human Action Recognition......Page 744 Conclusion......Page 747 References......Page 748 Introduction......Page 749 Metric Learning......Page 750 Neighborhood Component Analysis......Page 751 Proposed Semi-supervised NCA......Page 752 Experiments and Discussions......Page 753 Conclusions......Page 755 References......Page 756 Introduction......Page 757 The And-Ridge and and-Valley Image......Page 758 Text Region Location......Page 760 Train a Character Classifier......Page 762 Component Grouping......Page 763 Experimental Results......Page 764 References......Page 766 Introduction......Page 768 Studio Setup......Page 769 Computational Model......Page 770 Experimental Results......Page 772 References......Page 774 Author Index......Page 776 The 2010 Pacific-Rim Conference on Multimedia (PCM 2010) was held in Shanghai at Fudan University, during September 21–24, 2010. Since its inauguration in 2000, PCM has been held in various places around the Pacific Rim, namely Sydney (PCM 2000), Beijing (PCM 2001), Hsinchu (PCM 2002), Singapore (PCM 2003), Tokyo (PCM 2004), Jeju (PCM 2005), Zhejiang (PCM 2006), Hong Kong (PCM 2007), Tainan (PCM 2008), and Bangkok (PCM 2009). PCM is a major annual international conference organized as a forum for the dissemination of state-of-the-art technological advances and research results in the fields of theoretical, experimental, and applied multimedia analysis and processing. PCM 2010 featured a comprehensive technical program which included 75 oral and 56 poster presentations selected from 261 submissions from Australia, Canada, China, France, Germany, Hong Kong, India, Iran, Italy, Japan, Korea, Myanmar, Norway, Singapore, Taiwan, Thailand, the UK, and the USA. Three distinguished researchers, Prof. Zhi-Hua Zhou from Nanjing University, Dr. Yong Rui from Microsoft, and Dr. Tie-Yan Liu from Microsoft Research Asia delivered three keynote talks to the conference. We are very grateful to the many people who helped to make this conference a s- cess. We would like to especially thank Hong Lu for local organization, Qi Zhang for handling the publication of the proceedings, and Cheng Jin for looking after the c- ference website and publicity. We thank Fei Wu for organizing the special session on large-scale multimedia search in the social network settings.