Advances in visual computing : 17th International Symposium, ISVC 2022, San Diego, CA, USA, October 3-5, 2022, proceedings, part II. / / edited by George Bebis, [and eight others]

• Pubblicazione: Cham, Switzerland : , : Springer, , [2022]; ©2022
• Descrizione fisica: 1 online resource (466 pages)
• Disciplina: 929.605
• Soggetto topico: Computer vision
• Persona (resp. second.): BebisGeorge
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Keynote Talks -- Towards Scaling Up GANs -- Sensible Machine Learning for Geometry -- Designing Augmented Reality for the Future of Work -- The Future of Visual Computing via Foundation Models (Banquet Keynote Talk) -- 3D Reconstruction: Leveraging Synthetic Data for Lightweight Reconstruction -- Human-AI Interaction in Visual Analytics: Designing for the "Two Black Boxes" Problem -- Contents - Part II -- Contents - Part I -- ST: Neuro-inspired Artificial Intelligence -- Brain Shape Correspondence Analysis Using Functional Maps -- 1 Introduction -- 2 Materials and Methods -- 2.1 Database -- 2.2 Methodology -- 3 Results -- 3.1 First Experiment -- 3.2 Second Experiment -- 3.3 Third Experiment -- 4 Conclusions -- References -- Biomimetic Oculomotor Control with Spiking Neural Networks -- 1 Introduction -- 2 Related Work -- 3 Eye Model and Neuromuscular Oculomotor Controller -- 4 Spiking Neurons -- 4.1 Encoding the Input Signals -- 4.2 Outputs -- 5 The SLiNet Model -- 5.1 Architecture -- 5.2 Training -- 6 Experiments -- 6.1 Eye Movements -- 6.2 Comparison to Human Eye Movements -- 7 Conclusions -- References -- Border Ownership, Category Selectivity and Beyond -- 1 Introduction -- 2 Implementation -- 2.1 Border-Ownership Coding Method -- 2.2 Category-Selective Coding Method -- 2.3 TcNet -- 3 Results -- 3.1 Datasets -- 3.2 Statistic Evaluation Criteria -- 4 Discussion -- 4.1 T-Junctions and Other 'KEY' Points -- 4.2 Global Context Awareness -- 4.3 Early Object Representation, 'PRoto-Object' -- 4.4 Relation to Biological Vision Systems -- 5 Summary -- References -- Sparse Kernel Transfer Learning -- 1 Introduction -- 2 Background -- 2.1 Background in Convolutional Neural Networks -- 2.2 Background in Sparse Coding -- 3 Methodology -- 3.1 Dictionary Learning -- 3.2 Initialization Techniques -- 3.3 Datasets. ; 3.4 Kernel Transfer Learning -- 4 Experiments and Results -- 4.1 Comparison with Other Initialization Methods -- 4.2 Learning with Less Labels -- 4.3 Breast Cancer Detection -- 4.4 Intepretability and Complexity -- 5 Conclusion -- References -- Applications -- Photobombing Removal Benchmarking -- 1 Introduction -- 2 Related Work -- 2.1 Traditional Methods -- 2.2 Deep Learning-based Methods -- 3 Photobombing Removal Benchmark -- 3.1 Benchmarking Dataset -- 3.2 Benchmarking Methods -- 4 Experiments -- 4.1 Performance Metrics -- 4.2 Experimental Results -- 5 Conclusion and Future Works -- References -- Automatic Detection and Recognition of Products and Planogram Conformity Analysis in Real Time on Store Shelves -- 1 Introduction -- 1.1 Features for Detection of Retails Products -- 1.2 Detection of Single Product -- 2 Clustering by Products Famillies -- 2.1 Multi-object Detection with ASIFT -- 2.2 Distance Normalisation -- 2.3 DBSCAN: Products Famillies -- 2.4 Shelf Planogram Conformity Rate -- 3 Experiments -- 3.1 Database -- 3.2 Evaluation Metrics -- 4 Conclusion -- References -- Enhancing Privacy in Computer Vision Applications: An Emotion Preserving Approach to Obfuscate Faces -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 Face Detection -- 3.2 Face Selection -- 3.3 Face Reconstruction -- 3.4 Color Adaptation -- 3.5 Cloning -- 4 Validation -- 4.1 Experiment -- 4.2 Results -- 5 Conclusion and Future Work -- References -- House Price Prediction via Visual Cues and Estate Attributes -- 1 Introduction -- 2 Related Work -- 3 Proposed Work -- 3.1 Data Collection -- 3.2 Computational Model -- 4 Experiments -- 4.1 Evaluation Metrics -- 4.2 Experimental Results -- 4.3 Ablation Studies -- 5 Conclusion and Future Works -- References -- DRB-Net: Dilated Residual Block Network for Infrared Image Restoration -- 1 Introduction -- 2 Related Work. ; 2.1 Non-learning Denoising Methods -- 2.2 Discriminative Learning Denoising Methods -- 2.3 Deep Learning for IR Imaging -- 3 Proposed Architecture -- 3.1 Why Dilated Convolution? -- 3.2 Residual Blocks -- 3.3 Architecture and Compared Methods -- 4 Dataset -- 4.1 Sample Preparation and Image Acquisition -- 4.2 Dataset Creation -- 4.3 Implementation -- 5 Experiments -- 5.1 DRB-Net Specification -- 5.2 Denoising of Synthetic Noisy Data -- 5.3 Generalization and Robustness Test -- 6 Conclusion and Future Work -- References -- Segmentation and Tracking -- Saliency Can Be All You Need in Contrastive Self-supervised Learning -- 1 Introduction -- 2 Motivation and Background -- 2.1 Related Work -- 2.2 Concrete Background -- 3 Implementation, Setup and Results -- 3.1 Setup and Datasets -- 3.2 Preliminary: Running SGD on NORCE-PV and MultiRes-PV Datasets -- 3.3 An Efficient Implementation -- 3.4 Using SGD as an Augmentation Policy in Contrastive SSL Algorithms -- 4 Discussion -- 5 Conclusions -- References -- GCEENet: A Global Context Enhancement and Exploitation for Medical Image Segmentation -- 1 Introduction -- 2 Related Work -- 2.1 Convolutional Neural Networks for Semantic Segmentation -- 2.2 Contextual Information Modeling -- 3 Proposed Architecture -- 3.1 Overview -- 3.2 Global Context Encoder Module -- 3.3 Local Distribution -- 3.4 Aggregator Module -- 3.5 Loss Function -- 4 Experiments and Discussion -- 4.1 Benchmark Datasets -- 4.2 Experiment Settings -- 5 Results and Discussion -- 5.1 Ablation Study -- 5.2 Comparison to Baseline Models -- 6 Conclusion -- References -- V2F: Real Time Video Segmentation with Apache Flink -- 1 Introduction -- 2 Related Work -- 3 Video2Flink Architecture -- 3.1 V2F Operators -- 4 Experiments -- 5 Conclusions and Future Work -- References -- Joint Discriminative and Metric Embedding Learning for Person Re-identification. ; 1 Introduction -- 2 Related Work -- 3 Proposed Approach -- 3.1 Classification Losses -- 3.2 Metric Learning Loss -- 3.3 Joint Classification and Metric Loss -- 3.4 Network Architecture -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Comparison with State-of-the-Art Methods -- 4.3 Ablation Study -- 5 Conclusions -- References -- Transformer Networks for Future Person Localization in First-Person Videos -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Problem Overview -- 3.2 Input Overview -- 3.3 Implementation Details -- 4 Experiments -- 4.1 Evaluation Metrics and Baselines -- 4.2 Quantitative Results -- 4.3 Additional Analysis -- 4.4 Inference Time Analysis -- 5 Conclusion -- References -- Virtual Reality -- VR-SFT: Reproducing Swinging Flashlight Test in Virtual Reality to Detect Relative Afferent Pupillary Defect -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 Swinging Flashlight Test in Virtual Reality -- 3.2 VR Implementation and Experimental Software -- 3.3 RAPD Scoring -- 4 Dataset -- 5 Data Analysis and Results -- 6 Discussion and Future Work -- References -- A Quantitative Analysis of Redirected Walking in Virtual Reality Using Saccadic Eye Movements -- 1 Introduction -- 2 Methodology -- 2.1 Simulation and Hardware -- 2.2 Simulation Tasks and Data Collection -- 2.3 Eye Tracking -- 2.4 Questionnaire -- 2.5 Demographics -- 3 Results -- 4 Conclusion and Future Work -- References -- A DirectX-Based DICOM Viewer for Multi-user Surgical Planning in Augmented Reality -- 1 Introduction -- 2 Related Work -- 2.1 Holographic DICOM Viewer Prototypes -- 2.2 Interaction with 3D Objects -- 3 System Design Overview -- 4 Direct3D-Based DICOM Viewer Implementation -- 4.1 Smartphones as User Input Devices -- 4.2 Functionalities -- 4.3 Marker-Based 3D Object Placement -- 5 User Interactions -- 5.1 Virtual 2D Plane Touch. ; 5.2 3D User Interaction -- 6 Experiments -- 7 Conclusions -- References -- Virtual-Reality Based Vestibular Ocular Motor Screening for Concussion Detection Using Machine-Learning -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Naive Bayes -- 3.2 Decision Tree -- 3.3 Random Forest -- 3.4 Support Vector Classifer -- 3.5 AdaBoost -- 3.6 Gaussian Process Classifier -- 3.7 Logistic Regression -- 3.8 Perceptron -- 3.9 Isolation Forest -- 3.10 One Class SVM -- 4 Experimental Analysis -- 4.1 Data Collection Using Virtual-Reality Headset -- 4.2 Data Splitting for Training and Testing -- 4.3 Qualitative Evaluation -- 4.4 Quantitative Evaluation -- 5 Conclusion -- References -- Posters -- GUILD - A Generator for Usable Images in Large-Scale Datasets -- 1 Introduction -- 2 Related Work -- 2.1 Manual Collection of Datasets -- 2.2 Synthetic Generation of Datasets -- 3 Implementation -- 3.1 Approach -- 3.2 Object Models -- 3.3 Environments -- 3.4 Label Generation -- 4 Evaluation -- 4.1 Evaluation Design -- 4.2 Evaluation Datasets -- 4.3 Accuracy -- 4.4 Generalizability -- 4.5 Variety -- 5 Conclusion and Future Work -- References -- Distributional Semantics of Line Charts for Trend Classification -- 1 Introduction -- 2 Dataset -- 3 Related Work -- 3.1 Information Graphic Description Generation -- 3.2 Prototype Learning -- 3.3 Bag of Words for Computer Vision -- 3.4 Distributional Semantics -- 4 Architecture and Methodology -- 4.1 Forming the Vocabulary -- 4.2 Line Chart Embeddings -- 4.3 Classification -- 5 Implementation -- 6 Experiments and Results -- 6.1 Classification Task -- 6.2 Results -- 7 Discussion -- 8 Conclusion -- References -- Deep Learning Hyperparameter Optimization for Breast Mass Detection in Mammograms -- 1 Introduction -- 2 Background and Motivation -- 2.1 End-to-End Pipeline -- 2.2 Genetic Algorithm -- 2.3 Binary Tournament Selection. ; 2.4 Simulated Binary Crossover (SBX).
• Titolo autorizzato: Advances in Visual Computing
• ISBN: 3-031-20716-5
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996503470203316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Computer Science