MultiMedia Modeling : 22nd International Conference, MMM 2016, Miami, FL, USA, January 4-6, 2016, Proceedings, Part II / / edited by Qi Tian, Nicu Sebe, Guo-Jun Qi, Benoit Huet, Richang Hong, Xueliang Liu

• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2016
• Edizione: 1st ed. 2016.
• Descrizione fisica: 1 online resource (XXIII, 433 p. 185 illus. in color.)
• Disciplina: 006.7
• Soggetto topico: Multimedia systems; Information storage and retrieval; Pattern perception; Data mining; Application software; Multimedia Information Systems; Information Storage and Retrieval; Pattern Recognition; Data Mining and Knowledge Discovery; Information Systems Applications (incl. Internet)
• Persona (resp. second.): TianQi; SebeNicu; QiGuo-Jun; HuetBenoit; HongRichang; LiuXueliang
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part II -- Contents - Part I -- Special Session Poster Papers (continued) -- Transfer Nonnegative Matrix Factorization for Image Representation -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 3.1 Nonnegative Matrix Factorization -- 3.2 Hessian Regularization -- 4 Transfer Nonnegative Matrix Factorization -- 4.1 Problem Definition -- 4.2 Proposed Approach -- 4.3 Optimization -- 5 Experiments -- 5.1 Dataset Description -- 5.2 Performance on Cross-Domain Datasets -- 6 Conclusion -- References -- Sentiment Analysis on Multi-View Social Data -- 1 Introduction -- 2 Related Works -- 2.1 Sentiment Analysis Datasets -- 2.2 Sentiment Analysis Approaches -- 3 The MVSA Dataset -- 3.1 Data Collection and Annotation -- 3.2 Data Analysis -- 4 Predicting Sentiment in Multi-view Data -- 4.1 Text-Based Approaches -- 4.2 Visual-Based Approaches -- 4.3 Multi-view Sentiment Analysis -- 5 Experiments -- 5.1 Results on Textual Messages -- 5.2 Results on Images -- 5.3 Results on Multi-View Data -- 6 Conclusion and Future Work -- References -- Single Image Super-Resolution via Convolutional Neural Network and Total Variation Regularization -- Abstract -- 1 Introduction -- 2 Overview of the SR Algorithm -- 3 Convolutional Neural Network for SR -- 3.1 Training Set Generation -- 3.2 Convolutional Neural Network for SR -- 4 Regularization Constraints for SR -- 4.1 Non-Local Similarity Regularization Constraint -- 4.2 Local Similarity Regularization Constraint -- 4.3 Fundamental Formula -- 5 Experimental Results -- 5.1 Datasets -- 5.2 Results and Comparison -- 6 Conclusion -- References -- An Effective Face Verification Algorithm to Fuse Complete Features in Convolutional Neural Network -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Network Structure -- 3.2 Feature Extraction -- 3.3 Verification. ; 4 Experiments -- 5 Conclusion -- References -- Driver Fatigue Detection System Based on DSP Platform -- Abstract -- 1 Introduction -- 2 Methodology -- 2.1 Face Detection -- 2.2 Eye Detection -- 2.3 Eye State Estimation -- 3 Experiment and Results -- 3.1 Experiment Setting -- 3.2 Experimental Results -- 4 Conclusion -- References -- Real-Time Grayscale-Thermal Tracking via Laplacian Sparse Representation -- 1 Introduction -- 2 Related Work -- 3 Bayesian Filtering for Object Tracking -- 4 Observation Model -- 4.1 Laplacian Sparse Representation -- 4.2 Candidate Likelihood -- 5 Experiments -- 5.1 Evaluation Settings -- 5.2 Evaluation Metrics -- 5.3 Comparison Results -- 5.4 Component Analysis -- 6 Conclusion -- References -- Efficient Perceptual Region Detector Based on Object Boundary -- 1 Introduction -- 2 Related Work -- 2.1 Superpixel -- 2.2 Local Detectors -- 2.3 General Object Proposal -- 3 CAR: The Method -- 3.1 Contour-Aware Superpixel (CAS) -- 3.2 Perceptual Regions Detection -- 4 Experiments -- 4.1 Under-Segmentation Error -- 4.2 Boundary Recall -- 4.3 CAR Detector Repeatability -- 5 Conclusions -- References -- 1D Barcode Region Detection Based on the Hough Transform and Support Vector Machine -- Abstract -- 1 Introduction -- 2 Proposed Method -- 2.1 Barcode Detection -- 2.2 Support Vector Machine -- 2.3 Hough Transform -- 2.4 Using the SVM Classifier to Judge Pieces of the Image -- 2.5 Post-processing -- 3 Experiments and Results Analysis -- 3.1 Datasets -- 3.2 Result -- 4 Conclusion -- Acknowledgment -- References -- Special Session Papers -- Client-Driven Strategy of Large-Scale Scene Streaming -- 1 Introduction -- 2 Related Works -- 3 Overview -- 4 Multiple-resolution 3D Space Adaptive Grid Creation -- 5 Scene Streaming Assemble Strategy -- 5.1 Dynamic Double Layer AOI (D-DLAOI) -- 5.2 Object Priority Determination and LOD Resolution. ; 6 Experimental Results -- 7 Conclusion and Future Work -- References -- SELSH: A Hashing Scheme for Approximate Similarity Search with Early Stop Condition -- 1 Introduction -- 2 Preliminaries -- 2.1 Problem Definition -- 2.2 Notations -- 3 Related Work -- 4 Our Method -- 4.1 LSH Function -- 4.2 Distance Measure, Linear Order and Early Stop Condition -- 4.3 Index Structure -- 4.4 Search Process -- 4.5 Complexity Analysis -- 5 Experimental Results -- 5.1 Set up -- 5.2 Selection of Appropriate Parameters -- 5.3 Comparison with SK-LSH and C2LSH -- 6 Conclusion -- References -- Learning Hough Transform with Latent Structures for Joint Object Detection and Pose Estimation -- 1 Introduction -- 2 Related Work -- 3 Our Approach -- 3.1 Hough-Based Object Detection -- 3.2 Latent Deformable Feature Model -- 3.3 Multiple Instance Learning for M2HT -- 4 Experiment -- 4.1 Experiment Settings -- 4.2 Object Detection -- 4.3 Car Pose Estimation -- 5 Conclusion -- References -- Consensus Guided Multiple Match Removal for Geometry Verification in Image Retrieval -- 1 Introduction -- 2 Approximate Feature Matching -- 3 Geometric Verification by Hough Voting -- 4 Consensus Guided Multiple Match Removal -- 5 Experiments -- 5.1 Datasets and Evaluation -- 5.2 Experimental Setup -- 5.3 Experimental Results -- 6 Conclusion -- References -- Locality Constrained Sparse Representation for Cat Recognition -- 1 Introduction -- 2 The Methodology -- 2.1 Overview -- 2.2 Problem Formalism for Sparse Feature Representation -- 2.3 Supervised Dictionary Learning Approach -- 2.4 Recognition Task -- 3 Experimental Results -- 3.1 Dataset and Experimental Settings -- 3.2 Performance Evaluation -- 4 Conclusion and Future Work -- References -- User Profiling by Combining Topic Modeling and Pointwise Mutual Information (TM-PMI) -- Abstract -- 1 Introduction -- 2 The Proposed Approach. ; 2.1 Framework of the Proposed Approach -- 2.2 Data Preprocessing -- 2.3 LDA from Description of User Pins -- 2.4 Pointwise Mutual Information (PMI) -- 2.5 Personal Topic Words Extraction -- 2.6 Pins Recommended Based User Profile -- 3 Experiments -- 3.1 Dataset -- 3.2 Perplexity -- 3.3 User Study -- 3.4 Influence of the Number of Topic Words on the Result -- 4 Conclusion and Future Work -- References -- Image Retrieval Using Color-Aware Tag on Progressive Image Search and Recommendation System -- 1 Introduction -- 2 Related Works and Preliminaries -- 2.1 Related Works -- 2.2 PISAR System and WAS Algorithm -- 3 CAT Algorithm -- 3.1 Offline Phase -- 3.2 Online Phase -- 4 Experiment -- 4.1 Experimental Environment -- 4.2 Optimizing the Parameters in the CAT Algorithm -- 4.3 Example of Image Retrieval -- 4.4 Image Retrieval Result -- 5 Conclusions -- References -- Advancing Iterative Quantization Hashing Using Isotropic Prior -- 1 Introduction -- 2 Related Work -- 3 Isotropic Iterative Quantization -- 3.1 Preliminaries -- 3.2 Improving ITQ Using the Isotropic Prior -- 4 Experiments -- 5 Conclusion -- References -- An Improved RANSAC Image Stitching Algorithm Based Similarity Degree -- Abstract -- 1 Introduction -- 2 The Improved RANSAC Based Similarity Degree -- 2.1 Transformation Matrix of Image Registration -- 2.2 Calculation Method for RANSAC Sampled -- 2.3 Feature Points Matching in Coarse Matching Step -- 3 Pretreatment -- 4 Experimental Results and Analysis -- 5 Conclusions -- References -- A Novel Emotional Saliency Map to Model Emotional Attention Mechanism -- Abstract -- 1 Introduction -- 2 Emotional Saliency Map -- 2.1 Color Emotion Space -- 2.2 Emotional Saliency Map Computation -- 3 Experiments -- 3.1 Data Set and Error Measure -- 3.2 Experiments on Horror Image Set -- 3.3 Experiments on MS Image Set -- 4 Conclusion -- Acknowlegment. ; References -- Automatic Endmember Extraction Using Pixel Purity Index for Hyperspectral Imagery -- Abstract -- 1 Introduction -- 2 Pixel Purity Index -- 3 Automatic Endmember Extraction Using Pixel Purity Index -- 3.1 Determining the Number of Endmembers Based on Noise Subspace Projection -- 3.2 Data Dimensionality Reduction by Improving Noise Covariance Matrix (NCM) Estimation for MNF Transformation -- 3.3 Experimental Results and Analysis -- 4 Conclusions -- Acknowledgment -- References -- A Fast 3D Indoor-Localization Approach Based on Video Queries -- 1 Introduction -- 2 Related Work -- 3 Fast 3D Indoor-Localization -- 3.1 Pipeline -- 3.2 Deblurring Query Images -- 3.3 Interactive Foreground Segmentation -- 3.4 Dynamic Scene Query for Localization -- 4 Graph Matching Verification -- 5 Experiments -- 6 Conclusion -- References -- Smart Ambient Sound Analysis via Structured Statistical Modeling -- 1 Introduction -- 2 Multilayer Based Ambient Sound Understanding -- 2.1 Audio Preprocessing -- 2.2 Structured Environmental Sound Modelling -- 2.3 Segment Based Adaptation -- 2.4 Audio Concept Estimation Using SVM -- 3 Experimental Configuration -- 3.1 Data Collections -- 3.2 Methodology and Evaluation Metrics -- 3.3 Competitors for Performance Comparison -- 4 Experiment Results -- 5 Conclusions -- References -- Discriminant Manifold Learning via Sparse Coding for Image Analysis -- 1 Introduction -- 2 Discriminant Manifold Learning via Sparse Coding (DML_SC) -- 2.1 Motivation -- 2.2 Dictionary Learning and Feature Regrouping -- 2.3 Graph Embedding -- 3 Experiment Results -- 3.1 Data Preparation and Representation -- 3.2 Face Recognition Results -- 3.3 Clustering Experiment on COIL20 Database -- 4 Conclusion -- References -- A Very Deep Sequences Learning Approach for Human Action Recognition -- Abstract -- 1 Introduction -- 2 Related Work. ; 2.1 Convolutional Neural Networks.
• Sommario/riassunto: The two-volume set LNCS 9516 and 9517 constitutes the thoroughly refereed proceedings of the 22nd International Conference on Multimedia Modeling, MMM 2016, held in Miami, FL, USA, in January 2016. The 32 revised full papers and 52 poster papers were carefully reviewed and selected from 117 submissions. In addition 20 papers were accepted for five special sessions out of 38 submissions as well as 7 demonstrations (from 11 submissions) and 9 video showcase papers. The papers are organized in topical sections on video content analysis, social media analysis, object recognition and system, multimedia retrieval and ranking, multimedia representation, machine learning in multimedia, and interaction and mobile. The special sessions are: good practices in multimedia modeling; semantics discovery from multimedia big data; perception, aesthetics, and emotion in multimedia quality modeling; multimodal learning and computing for human activity understanding; and perspectives on multimedia analytics.
• Titolo autorizzato: MultiMedia Modeling
• ISBN: 3-319-27674-3
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910481962203321
• Lo trovi qui: Univ. Federico II
• Serie: Information Systems and Applications, incl. Internet/Web, and HCI ; ; 9517