Advances in Multimedia Information Processing - PCM 2016: 17th Pacific-Rim Conference on Multimedia, Xi´ an, China, September 15-16, 2016, Proceedings, Part II

Front Matter....Pages I-XIX
A Global-Local Approach to Extracting Deformable Fashion Items from Web Images....Pages 1-12
Say Cheese: Personal Photography Layout Recommendation Using 3D Aesthetics Estimation....Pages 13-23
Speech Enhancement Using Non-negative Low-Rank Modeling with Temporal Continuity and Sparseness Constraints....Pages 24-32
Facial Animation Based on 2D Shape Regression....Pages 33-42
A Deep CNN with Focused Attention Objective for Integrated Object Recognition and Localization....Pages 43-53
An Accurate Measurement System for Non-cooperative Spherical Target Based on Calibrated Lasers....Pages 54-63
Integrating Supervised Laplacian Objective with CNN for Object Recognition....Pages 64-73
Automatic Color Image Enhancement Using Double Channels....Pages 74-83
Deep Ranking Model for Person Re-identification with Pairwise Similarity Comparison....Pages 84-94
Cluster Enhanced Multi-task Learning for Face Attributes Feature Selection....Pages 95-104
Triple-Bit Quantization with Asymmetric Distance for Nearest Neighbor Search....Pages 105-115
Creating Spectral Words for Large-Scale Hyperspectral Remote Sensing Image Retrieval....Pages 116-125
Rapid Vehicle Retrieval Using a Cascade of Interest Regions....Pages 126-135
Towards Drug Counterfeit Detection Using Package Paperboard Classification....Pages 136-146
Dynamic Strategies for Flow Scheduling in Multihoming Video CDNs....Pages 147-158
Homogenous Color Transfer Using Texture Retrieval and Matching....Pages 159-168
Viewpoint Estimation for Objects with Convolutional Neural Network Trained on Synthetic Images....Pages 169-179
Depth Extraction from a Light Field Camera Using Weighted Median Filtering....Pages 180-189
Scale and Topology Preserving SIFT Feature Hashing....Pages 190-199
Hierarchical Traffic Sign Recognition....Pages 200-209
Category Aggregation Among Region Proposals for Object Detection....Pages 210-220
Exploiting Local Feature Fusion for Action Recognition....Pages 221-230
Improving Image Captioning by Concept-Based Sentence Reranking....Pages 231-240
Blind Image Quality Assessment Based on Local Quantized Pattern....Pages 241-251
Sign Language Recognition with Multi-modal Features....Pages 252-261
Heterogeneous Convolutional Neural Networks for Visual Recognition....Pages 262-274
Recognition Oriented Feature Hallucination for Low Resolution Face Images....Pages 275-284
Learning Robust Multi-Label Hashing for Efficient Image Retrieval....Pages 285-295
Abnormal Event Detection and Localization by Using Sparse Coding and Reconstruction....Pages 296-305
Real-Time Video Dehazing Based on Spatio-Temporal MRF....Pages 306-314
Dynamic Contour Matching for Lossy Screen Content Picture Intra Coding....Pages 315-325
A Novel Hard-Decision Quantization Algorithm Based on Adaptive Deadzone Offset Model....Pages 326-334
Comparison of Information Loss Architectures in CNNs....Pages 335-345
Fast-Gaussian SIFT for Fast and Accurate Feature Extraction....Pages 346-354
An Overview+Detail Surveillance Video Player: Information-Based Adaptive Fast-Forward....Pages 355-365
Recurrent Double Features: Recurrent Multi-scale Deep Features and Saliency Features for Salient Object Detection....Pages 366-375
Key Frame Extraction Based on Motion Vector....Pages 376-386
Haze Removal Technology Based on Physical Model....Pages 387-395
Robust Uyghur Text Localization in Complex Background Images....Pages 396-405
Learning Qualitative and Quantitative Image Quality Assessment....Pages 406-416
An Analysis-Oriented ROI Based Coding Approach on Surveillance Video Data....Pages 417-427
A Stepwise Frontal Face Synthesis Approach for Large Pose Non-frontal Facial Image....Pages 428-438
Nonlinear PCA Network for Image Classification....Pages 439-448
Salient Object Detection in Video Based on Dynamic Attention Center....Pages 449-457
Joint Optimization of a Perceptual Modified Wiener Filtering Mask and Deep Neural Networks for Monaural Speech Separation....Pages 458-468
Automatic Extraction and Construction Algorithm of Overpass from Raster Maps....Pages 469-478
Geometric and Tongue-Mouth Relation Features for Morphology Analysis of Tongue Body....Pages 479-489
Perceptual Asymmetric Video Coding for 3D-HEVC....Pages 490-497
Recognition of Chinese Sign Language Based on Dynamic Features Extracted by Fast Fourier Transform....Pages 498-507
Enhanced Joint Trilateral Up-sampling for Super-Resolution....Pages 508-517
Learning to Recognize Hand-Held Objects from Scratch....Pages 518-526
Audio Bandwidth Extension Using Audio Super-Resolution....Pages 527-539
Jointly Learning a Multi-class Discriminative Dictionary for Robust Visual Tracking....Pages 540-549
Product Image Search with Deep Attribute Mining and Re-ranking....Pages 550-560
A New Rate Control Algorithm Based on Region of Interest for HEVC....Pages 561-570
Deep Learning Features Inspired Saliency Detection of 3D Images....Pages 571-579
No-Reference Quality Assessment of Camera-Captured Distortion Images....Pages 580-589
GIP: Generic Image Prior for No Reference Image Quality Assessment....Pages 590-599
Objective Quality Assessment of Screen Content Images by Structure Information....Pages 600-608
CrowdTravel: Leveraging Heterogeneous Crowdsourced Data for Scenic Spot Profiling and Recommendation....Pages 609-616
Context-Oriented Name-Face Association in Web Videos....Pages 617-628
Social Media Profiler: Inferring Your Social Media Personality from Visual Attributes in Portrait....Pages 629-639
SSFS: A Space-Saliency Fingerprint Selection Framework for Crowdsourcing Based Mobile Location Recognition....Pages 640-649
Multi-view Multi-object Tracking Based on Global Graph Matching Structure....Pages 650-659
Accelerating Large-Scale Human Action Recognition with GPU-Based Spark....Pages 660-669
Adaptive Multi-class Correlation Filters....Pages 670-679
Deep Neural Networks for Free-Hand Sketch Recognition....Pages 680-688
Fusion of Thermal and Visible Imagery for Effective Detection and Tracking of Salient Objects in Videos....Pages 689-696
RGB-D Camera based Human Limb Movement Recognition and Tracking in Supine Positions....Pages 697-704
Scene Parsing with Deep Features and Spatial Structure Learning....Pages 705-714
Semi-supervised Learning for Human Pose Recognition with RGB-D Light-Model....Pages 715-722
Back Matter....Pages 723-737
....Pages 739-743