دانلود کتاب Advances in Multimedia Information Processing -- Pcm 2015: 16th Pacific-Rim Conference on Multimedia, Gwangju, South Korea, September 16-18, 2015, Proceedings, Part I

فهرست مطالب :

Preface......Page 6
Organization......Page 7
Contents – Part I......Page 10
Contents – Part II......Page 17
Image and Audio Processing......Page 23
1 Introduction......Page 24
2 Otsu Thresholding......Page 25
3.2 Internal Generative Mechanism......Page 26
3.3 Regrouping the Controversial Pixels......Page 27
4.2 Experimental Results......Page 29
5 Conclusion......Page 31
References......Page 32
1 Introduction......Page 34
2.1 Motivation......Page 36
2.2 Robust Face Landmark Detector Training......Page 37
2.4 Blind Image Deblurring......Page 38
3.1 Experiments on Synthesised Dataset and Real Images......Page 39
3.4 Rolling Guidance Face Deblurring......Page 40
References......Page 42
1 Introduction......Page 44
2.1 Non-uniform Blur Model......Page 45
2.3 The Initial Kernel Estimation Using Gyro Data......Page 46
2.4 Kernel Refinement......Page 47
3 Experimental Results......Page 48
4 Conclusion......Page 51
References......Page 52
1 Introduction......Page 53
2 Conventional Methods......Page 54
3.1 Partition Search Area......Page 56
3.2 Object Identification......Page 57
4 Experiment Results......Page 58
References......Page 61
Multimedia Content Analysis......Page 63
1.1 Related Work on Subspace Clustering......Page 64
2 Two-Step Greedy Subspace Clustering......Page 66
2.2 Second Step: Greedy Subspace Clustering......Page 67
3 Experiments......Page 68
3.1 Motion Segmentation......Page 69
3.2 Face Clustering......Page 70
References......Page 72
1 Introduction......Page 74
2 Overview of Proposed Method......Page 76
4 Semi-Supervised Clustering......Page 77
5 Supervision Information Establishment......Page 78
6 Experiments and Results......Page 79
References......Page 83
1 Introduction......Page 85
2.2 Our Supervised Dictionary Learning......Page 87
2.3 Optimization Algorithm......Page 88
3.2 Comparison Methods and Evaluation Criteria......Page 90
3.3 Experimental Results and Analysis......Page 91
References......Page 92
1 Introduction......Page 94
2 Large Margin Nearest Neighbor......Page 96
3 Adaptive Margin Nearest Neighbor......Page 97
4.1 Experiment Setting......Page 98
4.3 Evaluation on VIPeR and CUHK......Page 99
References......Page 101
1 Introduction......Page 104
2.1 Camera Model......Page 106
2.2 Estimation of T......Page 107
2.3 Estimation of a......Page 108
3 Experimental Results......Page 109
3.1 GME Evaluation......Page 110
3.2 Feature Descriptor Evaluation......Page 111
References......Page 112
Image and Audio Processing......Page 114
1 Introduction......Page 115
2.1 Image Manipulation Forensics Model......Page 116
2.2 Security Evaluation and Attacks......Page 117
3 A Case Study with Resampling Forging Attack......Page 119
4 Experimental Results......Page 120
References......Page 122
1 Introduction......Page 124
2.1 Dictionary Construction for Two Target Region Cases......Page 126
3 Experimental Results......Page 128
4 Conclusion......Page 130
References......Page 131
1 Introduction......Page 132
2 Related Work......Page 134
3.1 Preliminary of Hierarchical Graph Cut......Page 135
3.3 Integration of Color Cue and Depth Cue......Page 136
3.4 Upscaling Boundary Refinement......Page 137
4.3 Running Time Evaluation......Page 139
References......Page 140
1 Introduction......Page 143
2 Overview......Page 144
3 Main Work......Page 145
3.1 Key Feature Points of a Component......Page 146
3.2 Two-Layer Geometric Constraint......Page 147
3.3 Sub-shape Selection......Page 148
4.1 Comparison with Previous Works......Page 150
References......Page 151
1 Introduction......Page 153
2 Ambisonics Method......Page 154
3 3D Panning Method with Sound Pressure Constraint at Two Ears......Page 156
4.4 Final Signals......Page 159
5.1 Objective Tests......Page 160
5.2 Subjective Tests......Page 161
References......Page 162
Multimedia Applications and Services......Page 164
1 Introduction......Page 165
2.1 Online Multi-target Tracking......Page 167
2.2 Active Camera Scheduling......Page 168
2.4 Final Trajectory Generation......Page 169
3.1 Experiment Setting......Page 170
3.2 Results......Page 171
4 Conclusion......Page 173
References......Page 174
1 Introduction......Page 176
2 Related Works......Page 177
3.1 Dirichlet Process Mixture Model......Page 178
3.2 Model Inference......Page 179
3.3 AMAM Tracking......Page 180
4.1 The AMAM Modeling......Page 181
4.2 Tracking System......Page 182
5 Conclusion......Page 184
References......Page 185
1 Introduction......Page 187
3 Proposed Method......Page 189
3.2 On-line Sample Generation......Page 190
4 Experimental Results......Page 193
References......Page 195
1 Introduction......Page 197
3 Multi-level Image Representation......Page 199
4 Online Segmentation......Page 201
5 Experimental Result......Page 202
References......Page 206
1 Background......Page 208
2 Unlimited Channel for Communication......Page 210
References......Page 214
Video Coding and Processing......Page 216
1 Introduction......Page 217
2.1 Ball Size Adaptive Tracking Window......Page 218
2.2 Volleyball Feature Likelihood Model......Page 220
3.1 Tracking Example and Evaluation Method......Page 221
3.2 Result and Comparison Analysis......Page 222
References......Page 224
1 Introduction......Page 226
2 Analysis......Page 228
3 The Proposed Scheme......Page 229
3.2 Multiple-Reference Scheme......Page 230
3.3 Global Reference Scheme......Page 231
3.4 Costs......Page 232
4 Experimental Results......Page 233
References......Page 235
1 Introduction......Page 237
2.2 Scene Surveillance Video Global Coding Scheme......Page 239
3 Global Object Representation Based on Model and Feature Parameters......Page 240
3.2 Location and Pose Representation......Page 241
3.4 Illumination Parameters Representation......Page 242
4.1 Experiment 1......Page 243
4.2 Experiment 2......Page 244
5 Conclusions......Page 245
References......Page 246
1 Introduction......Page 247
2 Foreground Detection via Sparse Error Compensation Based Incremental PCA......Page 248
2.2 Two-Step Optimization Algorithm......Page 249
3 Experiments......Page 252
References......Page 255
Multimedia Representation Learning......Page 257
1 Introduction......Page 258
2 Principal Pyramidal Convolution......Page 259
3 Experiment......Page 260
3.2 Comparisons on Different Networks......Page 261
3.3 Comparisons on Different Dimensions......Page 263
References......Page 265
1 Introduction......Page 267
2 Related Work......Page 268
3.1 Low-Level and High-Level Descriptions of Graphlets......Page 269
3.2 Sparsity-Constrained Graphlets Ranking......Page 271
3.3 Gaze Shifting Kernel and SVM Training......Page 272
4.1 Comparison with the State-of-the-Art......Page 273
4.2 Parameters Analysis......Page 274
4.3 Visualization Results......Page 275
References......Page 276
1 Introduction......Page 278
2.1 The Motivation of the TPLRMC......Page 280
2.2 The First Phase of the TPLRMC......Page 281
2.4 Analysis of the TPLRMC......Page 282
3 Experiments......Page 283
3.2 Experimental Results......Page 284
References......Page 286
1 Introduction......Page 288
2.2 Building the Multiple Multi-level Auto-Encoders......Page 290
2.4 The Weight Assigned for Each Feature......Page 291
3.1 The MNIST......Page 292
3.2 The CIFAR 10......Page 293
4 Conclusion......Page 295
References......Page 296
1 Introduction......Page 298
2 Related Work......Page 300
3 The Proposed Method......Page 301
4.2 Result and Discussion......Page 304
5 Conclusion......Page 306
References......Page 307
Regular Poster Session......Page 309
1 Introduction......Page 310
2 Locally Weighted &hx2113;1 Regularization......Page 312
4 Experimental Results......Page 315
4.2 Comparisons of Subjective Results......Page 316
5 Conclusions......Page 318
References......Page 319
1 Introduction......Page 321
2.1 Linear Regression......Page 323
2.2 Kernel Regression......Page 324
3.1 Online Correlation Filter Update......Page 325
4 Experiments......Page 327
References......Page 329
1 Introduction......Page 332
2.2 Global Tone Mapping Operation......Page 334
3.1 Unified TMO......Page 335
3.3 Integer TMO for the Intermediate Format......Page 336
3.4 Fixed-Point Arithmetic......Page 338
4 Experimental and Evaluation Results......Page 339
4.1 Comparison of Tone-Mapped LDR Images......Page 340
4.2 Comparison of the Memory Usage......Page 341
4.3 Comparison of the Processing Time......Page 342
References......Page 343
1 Introduction......Page 345
2 Proposed Human Action Recognition System......Page 346
2.1 Multi-view Skeleton Integration......Page 347
2.2 Snapshot Feature Extraction......Page 348
2.3 Temporal Feature Extraction......Page 349
3 Experiment and Results......Page 350
4 Conclusion......Page 352
References......Page 353
Abstract......Page 355
1.1 Related Work......Page 356
2.1 Multizone Soundfield Model......Page 357
2.3 Loudspeaker Weight Coefficients......Page 358
3.1 Simplification Results......Page 359
3.2 Simulation Results and Comparison Analysis......Page 361
3.3 Subjective Results and Comparison Analysis......Page 363
References......Page 364
1 Introduction......Page 365
2.1 Directional Audio Coding (DirAC)......Page 366
2.2 3D Audio Spatial Localization Quantization Method......Page 367
2.3 The Existing Compression Approaches of Spatial Parameters......Page 368
3.1 Proposed Spatial Parameter Compression Scheme......Page 369
3.2 Multi-channel Object-Based Spatial Parameter Compression Approach......Page 370
4.1 Objective Quality Evaluation......Page 371
4.2 Subjective Quality Evaluation......Page 372
References......Page 374
1 Introduction......Page 376
2 Active Vision System......Page 377
3 Target Tracking......Page 378
3.2 Gradients in Fixed Directions......Page 379
3.4 Improvement......Page 380
4 FPGA Implementation......Page 381
6.1 Hardware Environment......Page 382
6.2 Target Tracking Experiment......Page 383
7 Conclusions......Page 384
References......Page 385
1 Introduction......Page 386
2 Video Summarization of Powerful Contents Based on OCSVM......Page 387
2.1 Extraction of Key Frames and Features......Page 388
2.2 Powerful Frames Selection with One Class SVM......Page 389
3 Experiments and Discussion......Page 390
4 Conclusion......Page 392
References......Page 393
1 Introduction......Page 394
2 Motivation......Page 395
3 The Methodology......Page 396
3.1 Multi-method Fusion via CRF......Page 397
3.2 Locality-Aware Multi-method Fusion......Page 398
4.1 Experimental Settings......Page 399
4.2 Results and Discussion......Page 400
5 Conclusion......Page 402
References......Page 403
1 Introduction......Page 404
2 Proposal......Page 405
2.2 Players\' Features Based Likelihood Model......Page 407
3 Experiment and Result......Page 409
References......Page 411
1 Introduction......Page 413
2 Related Works......Page 414
3.1 Algorithm Framework......Page 415
3.2 Affinity Matrix Approximation......Page 416
4.1 Implemention......Page 417
4.3 Tonal Values Adjustments......Page 418
5 Discussions and Conclusions......Page 419
References......Page 420
1 Introduction......Page 422
2.1 Pre-processing......Page 424
2.2 Initial Saliency Map Calculation......Page 425
3 Experiments......Page 426
3.1 Performance Evalation on ASD and MSRA Datasets......Page 428
3.2 Effectiveness of Saliency Map Refinement......Page 429
4 Conclusion......Page 430
References......Page 431
1 Introduction......Page 432
2.1 High-Resolution Reconstruction Weights......Page 434
3 High-Resolution Reconstructed-Weights Representation......Page 435
3.2 Face Hallucination via HRR......Page 436
4.1 Experiment Settings......Page 437
4.2 Results Comparison......Page 438
4.3 Influence of Parameters......Page 439
5 Conclusion......Page 440
References......Page 441
1 Introduction......Page 442
2 Related Work......Page 443
3.1 Overview......Page 444
3.2 Surface Reflection......Page 445
3.3 Subsurface Reflection......Page 446
4 Results......Page 448
5 Conclusions......Page 450
References......Page 451
1 Introduction......Page 453
2 Related Work......Page 454
3.2 Analysis of Depth-Bit Assignment......Page 455
4 Results and Discussion......Page 456
4.1 Evaluation of Depth-Bit Assignment-Methods......Page 457
4.2 Evaluation of x264 Encoding Parameter Settings......Page 458
4.3 Depth Compression for Real-Time 3D Reconstruction......Page 460
5 Conclusion......Page 461
References......Page 462
1 Introduction......Page 464
2 Linear Regression Classification......Page 465
3 Marginal Fisher Regression Classification......Page 467
4.2 Experiment on PIE Dataset......Page 470
4.3 Experiment on AR Dataset......Page 471
References......Page 472
1 Introduction......Page 474
2 The Temporally Adaptive Quantization Algorithm......Page 475
3.1 The Proposed delta - rho Model......Page 478
3.2 The Improved Quantization Control Algorithm......Page 480
4 Simulation Results and Analysis......Page 481
Acknowledgment......Page 482
References......Page 483
1 Introduction......Page 484
2 Label Correlation Based Sampling Strategy......Page 486
3.2 Complete Algorithm......Page 487
4 Experiments......Page 488
4.1 On Image Datasets......Page 489
4.2 On Non-image Datasets......Page 491
References......Page 492
1 Introduction......Page 494
2 Proposed Technique......Page 496
2.1 Text Candidate Region Detection......Page 497
2.2 Multi-modal Method for Text Detection/Recognition......Page 499
3 Experimental Results......Page 500
3.2 Validating Multi-modality Through Text Detection......Page 501
3.3 Validating Multi-modality Through Recognition......Page 502
4 Conclusion and Future Work......Page 503
References......Page 504
1 Introduction......Page 506
2 Proposed Methodology......Page 508
2.1 Multi-spectral Images for Reducing Degradation Effect......Page 509
2.2 Multi-spectral Fusion-1 for Text Frame Enhancement......Page 510
3 Experimental Results......Page 512
3.1 Experiments on Measuring Quality of the Enhanced Frame......Page 513
3.3 Validating Enhancement Through Recognition......Page 514
Acknowledgment......Page 515
References......Page 516
1 Introduction......Page 518
2 Related Work......Page 519
3 Video Text Segmentation......Page 521
4 Text Extraction......Page 522
5 Best Extraction Schemes Choosing......Page 523
6.2 Performance of Text Extraction......Page 524
6.3 Recognition Performance with Best Scheme Choosing......Page 525
References......Page 527
1 Introduction......Page 529
2 Related Works......Page 530
3 Proposed Methods......Page 531
3.2 Regression by K-Nearest Neighbors......Page 533
4 Experimental Results......Page 534
4.2 Regression by K-Nearest Neighbors......Page 535
5 Conclusion......Page 537
References......Page 538
1 Introduction......Page 539
2.1 Motivation......Page 540
2.2 Proposed BWE Method......Page 541
3.1 Auto-Encoders......Page 542
4.1 Training Auto-Encoders......Page 544
4.3 Performance Evaluation......Page 545
5 Conclusions......Page 546
References......Page 547
1 Introduction......Page 549
2 Hybrid Part Localization......Page 551
3.1 Definitions......Page 552
3.2 Optimization......Page 553
4.2 Part Localization Results......Page 554
4.3 Segmentation Results......Page 555
4.4 Recognition Results......Page 556
5 Conclusion......Page 557
References......Page 558
1 Introduction......Page 560
2.1 RBF Interpolation......Page 561
2.2 CS Reconstruction Algorithm......Page 563
3.1 Data Sets......Page 565
3.4 Comparison with Other Methods......Page 566
References......Page 568
1 Introduction......Page 570
2.2 Representing Video Content with Revised TF-IDF......Page 572
2.3 Construction of Video Map by Maximum Spanning Tree......Page 573
3 Construction of Concept Map by Integrating Wikipedia Knowledge and Lecture Videos......Page 574
3.2 Constructing Directed Concept Map by Discovering the Prerequisite Relationships Between Concepts......Page 575
4 Experiments......Page 576
4.1 Evaluation of Video Maps......Page 577
4.2 Evaluation of Concept Maps......Page 578
References......Page 579
1 Introduction......Page 581
2 Proposed Algorithm......Page 582
2.1 Discriminative Global Model......Page 583
2.2 Generative Local Model......Page 585
3.1 Implementation Details......Page 586
3.2 Performance Evaluation......Page 587
References......Page 589
1 Introduction......Page 591
2.1 Contour Based Meanshift Target Locating......Page 592
2.2 Appearance Model Combing Global and Local Layers......Page 594
2.3 Dynamic Shape Model......Page 595
2.4 Multi-cues Active Contours and Curve Evolution......Page 596
3.2 Qualitative and Quantitative Analysis......Page 598
4 Conclusion......Page 600
References......Page 601
1 Introduction......Page 602
2.1 Classifiers Training......Page 605
2.3 Attribute Confidence and Saliency Matching Method......Page 606
3.1 Dataset and Evaluation Protocol......Page 607
3.2 Results and Discussions......Page 608
References......Page 610
1 Introduction......Page 612
2 Related Work......Page 613
3 Light Field Editing Framework......Page 614
3.2 Downsampling-Upsampling Propagation Framework......Page 615
4 Results......Page 619
References......Page 620
1 Introduction......Page 622
2 Related Work......Page 623
3 System Pipeline......Page 624
4.1 Embedded Deformation [4]......Page 625
4.2 Construct Deformation Graph......Page 626
4.3 Optimization......Page 627
5.2 Animating Disproportionate Avatar......Page 628
6 Conclusion......Page 630
References......Page 631
Visual Understanding and Recognition on Big Data......Page 632
1 Introduction......Page 633
2.1 Vectorial Representation......Page 635
2.2 Fast Similarity Search......Page 637
2.4 Complexity......Page 638
3.1 Experimental Setting......Page 639
3.2 Experimental Results......Page 641
References......Page 642
1 Introduction......Page 644
2.1 Structure Features......Page 646
2.3 CNN-Based Features......Page 647
3 Text Line Formation......Page 648
4 String Splitting......Page 649
5 Experimental Results......Page 650
References......Page 652
1 Introduction......Page 654
2.1 Fisher Vector......Page 656
2.2 Exploring the Implicit Group Structure......Page 657
2.3 Model Learning......Page 658
3.2 Experiments on HMDB51 Dataset......Page 659
References......Page 661
1 Introduction......Page 663
2.1 Model Structure for Human Parsing......Page 664
2.2 Multi Channel Segmentation by Shape Boltzmann Machine Network......Page 665
2.3 Similarity Measurement of the Curve and Curve Correction......Page 667
3.1 Dataset and Implements......Page 669
3.2 Results and Performances......Page 670
4 Conclusion......Page 671
References......Page 672
1 Introduction......Page 674
2 Depth-Based Stereoscopic Projection Approach......Page 675
2.1 Three-Dimensional Reconstruction and Stereographic Projection......Page 676
2.2 Processing Based on Characteristics of Projected Images......Page 678
2.3 Generating Depth Saliency Map and 3D Saliency Map......Page 679
3 The Experimental Results and Analysis......Page 680
4 Conclusion......Page 682
References......Page 683
Coding and Reconstruction of Multimedia Data with Spatial-Temporal Information......Page 684
1 Introduction......Page 685
2.1 A Fast and Effective SISR Method Based on Mixture of Experts......Page 687
3.1 Blur Kernels and Scaling Factors......Page 688
3.2 Datasets and Features......Page 689
4.1 SISR Methods w.r.t. Mismatched Blur Kernels......Page 690
5 Conclusions......Page 693
References......Page 694
1 Introduction......Page 696
2.1 Motivation of the Prediction Model......Page 697
2.2 Extracting the Objective Parameters......Page 698
3.1 Data Pre-processing......Page 700
3.2 Principle Components Extraction......Page 701
4.1 Training and Testing Data Set......Page 702
4.2 Algorithm Evaluation......Page 703
References......Page 705
1 Introduction......Page 707
2 Proposed Physical Properties Based Method......Page 709
2.1 Verification of Panning Law Based on Physical Properties of Sound Field......Page 710
2.2 Estimation of Phantom Source for Symmetric Arrangement Case......Page 711
2.3 Estimation of Phantom Source for Asymmetric Arrangement Case......Page 712
3.1 Objective Experiments......Page 713
3.2 Subjective Experiment......Page 716
References......Page 717
1 Introduction......Page 719
2.2 Two-Layer Knowledge Dictionary for Eliminating Global Object Redundancy......Page 721
3 Proposed Method......Page 722
3.1 Two-Layer Dictionary Learning......Page 723
3.2 Dictionary-Based Coding Scheme for Moving Vehicles......Page 724
4 Experimental Results......Page 725
5 Conclusion......Page 727
References......Page 728
1 Introduction......Page 729
2 Proposed Method......Page 731
2.1 Depth Map Skipping......Page 732
2.2 Depth Map Projection......Page 733
3.1 Data Acquisition and Prototypes......Page 734
3.2 Experiments and Results......Page 735
References......Page 737
Author Index......Page 738