Image Analysis and Processing - ICIAP 2022 : 21st International Conference, Lecce, Italy, May 23-27, 2022, Proceedings, Part I / / Stan Sclaroff [and four others], editors

• Pubblicazione: Cham, Switzerland : , : Springer Nature Switzerland AG, , [2022]; ©2022
• Descrizione fisica: 1 online resource (814 pages)
• Disciplina: 006.37
• Soggetto topico: Image analysis; Image processing
• Persona (resp. second.): SclaroffStan
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Contents - Part III -- Brave New Ideas -- A Lightweight Model for Satellite Pose Estimation -- 1 Introduction -- 2 Methodology and Data -- 2.1 Processing Pipeline -- 2.2 The Dataset -- 3 Experimental Results -- 4 Conclusions -- References -- Imitation Learning for Autonomous Vehicle Driving: How Does the Representation Matter? -- 1 Introduction -- 2 Related Work -- 3 Materials and Methods -- 3.1 Dataset -- 3.2 Benchmark -- 3.3 The Investigated CIL Method -- 3.4 Analysis of the Input Representation -- 3.5 Training Procedure -- 4 Experimental Results -- 5 Conclusions -- References -- LessonAble: Leveraging Deep Fakes in MOOC Content Creation -- 1 Introduction -- 2 Methodology -- 2.1 Voice Generation -- 2.2 Video Generation -- 2.3 Lip-syncing -- 3 Use Case -- 4 Conclusion -- References -- An Intelligent Scanning Vehicle for Waste Collection Monitoring -- 1 Introduction -- 2 Related Work -- 3 Intelligent Waste Recognition System -- 4 Hardware Design -- 5 Software Design -- 5.1 Data Preprocessing -- 5.2 Intelligent Waste Segmentation -- 5.3 Result Analysis and Communication -- 6 Results -- 7 Conclusion -- References -- Morphological Galaxies Classification According to Hubble-de Vaucouleurs Diagram Using CNNs -- 1 Introduction -- 2 Problem Statement -- 2.1 Galaxy Zoo Dataset -- 2.2 Data Augmentation -- 3 Method -- 3.1 Proposed Architecture -- 3.2 CNNs Based on Well-Known Backbones -- 4 Experimental Results -- 5 Conclusions -- References -- Biomedical and Assistive Technology -- Pulmonary-Restricted COVID-19 Informative Visual Screening Using Chest X-ray Images from Portable Devices -- 1 Introduction -- 2 Materials -- 3 Methodology -- 3.1 Region of Interest Extraction -- 3.2 COVID-19 Screening -- 4 Results and Discussion -- 4.1 Training Results -- 4.2 Test Results. ; 5 Conclusions -- References -- Comparison of Different Supervised and Self-supervised Learning Techniques in Skin Disease Classification -- 1 Introduction -- 2 Related Work -- 2.1 Self-supervised Learning -- 2.2 On ISIC 2019 Dataset -- 3 Method -- 3.1 Loss and Optimizer -- 3.2 Choosing CNN and Input Image Size -- 3.3 Data Augmentations -- 4 Experimental Results -- 4.1 Self-supervised Experiments -- 5 Conclusion and Future Work -- References -- Unsupervised Deformable Image Registration in a Landmark Scarcity Scenario: Choroid OCTA -- 1 Introduction -- 2 Materials and Methods -- 2.1 Dataset -- 2.2 Network Architecture -- 2.3 Training Details -- 2.4 Baseline Methods -- 2.5 Evaluation Metric -- 3 Results and Discussion -- 3.1 Quantitative Evaluation -- 3.2 Qualitative Evaluation -- 4 Conclusions -- References -- Leveraging CycleGAN in Lung CT Sinogram-free Kernel Conversion -- 1 Introduction -- 2 Methodology -- 2.1 Pre-processing -- 2.2 Kernel Conversion -- 3 Experimental Setup -- 4 Results -- 5 Conclusion -- References -- Investigating One-Class Classifiers to Diagnose Alzheimer's Disease from Handwriting -- 1 Introduction -- 2 Related Works -- 3 One-class Classifiers -- 3.1 RNSA -- 3.2 Isolation Forest -- 3.3 One-class Support Vector Machine -- 4 Experimental Results -- 4.1 Dataset -- 4.2 Features Selection -- 4.3 Performance Evaluation -- 5 Discussion and Conclusions -- References -- Learning Unrolling-Based Neural Network for Magnetic Resonance Imaging Reconstruction -- 1 Introduction -- 2 Related Work -- 2.1 Deep Learning for MR Imaging -- 2.2 Unrolling-Based Deep Learning Approaches -- 3 Approach -- 3.1 Overall Architecture -- 3.2 Improved Swin Transformer Blocks of UTrans -- 4 Experiments -- 4.1 Datasets and Baseline Models -- 4.2 Implementation Details -- 4.3 Result and Evaluation -- 4.4 Ablation Analysis -- 5 Conclusion -- References. ; Machine Learning to Predict Cognitive Decline of Patients with Alzheimer's Disease Using EEG Markers: A Preliminary Study -- 1 Introduction -- 2 EEG Features -- 3 Cognitive Tests and Scales -- 4 Experimental Results -- 5 Conclusions -- References -- Improving AMD Diagnosis by the Simultaneous Identification of Associated Retinal Lesions -- 1 Introduction -- 2 Materials and Methods -- 2.1 Prediction Loss -- 2.2 Network Architecture -- 2.3 Data -- 2.4 Training Details -- 3 Results and Discussion -- 4 Conclusions -- References -- Eye Diseases Classification Using Deep Learning -- 1 Introduction -- 1.1 Motivation -- 1.2 Overview of the Study -- 2 Related Work -- 2.1 Diabetic Retinopathy -- 2.2 Glaucoma -- 2.3 Cataract -- 3 Datasets -- 4 Synergic Deep Learning -- 5 Segmentation -- 6 Experiments Results -- 6.1 Initial Approach -- 6.2 Individual Diseases Classification -- 6.3 Multiple Diseases Classification -- 6.4 Comparison to Standard DCNN Model -- 7 Discussion -- 8 Conclusions -- References -- A Two-Step Radiologist-Like Approach for Covid-19 Computer-Aided Diagnosis from Chest X-Ray Images -- 1 Introduction -- 2 Datasets -- 3 Radiological Report -- 3.1 Architecture -- 3.2 Dealing with Uncertain Labels -- 4 COVID Diagnosis -- 5 Experiments -- 6 Conclusions -- References -- UniToChest: A Lung Image Dataset for Segmentation of Cancerous Nodules on CT Scans -- 1 Introduction -- 2 Background and Related Works -- 3 The UniToChest Dataset -- 4 Methodology -- 4.1 Data Preprocessing -- 4.2 Network Architecture -- 4.3 Training Procedure -- 5 Results and Discussion -- 5.1 Nodules Segmentation -- 5.2 Detection -- 6 Conclusion and Future Works -- References -- Optimized Fusion of CNNs to Diagnose Pulmonary Diseases on Chest X-Rays -- 1 Introduction -- 2 Materials -- 3 Methods -- 3.1 Pre-processing -- 3.2 Training of Single CNNs -- 3.3 Ensemble Optimization. ; 4 Results and Discussions -- 5 Conclusions -- References -- High/Low Quality Style Transfer for Mutual Conversion of OCT Images Using Contrastive Unpaired Translation Generative Adversarial Networks -- 1 Introduction -- 2 Methodology -- 3 Results and Discussion -- 4 Conclusions -- References -- Real-Time Respiration Monitoring of Neonates from Thermography Images Using Deep Learning -- 1 Introduction -- 2 Materials and Methods -- 2.1 Experimental Setup and Dataset -- 2.2 Data Preprocessing -- 2.3 Detector Training and Validation -- 2.4 Respiration Extraction -- 2.5 Real-Time Feasibility on Embedded GPUs -- 3 Results and Discussion -- 3.1 Detector Accuracy -- 3.2 Respiration Extraction -- 3.3 Inference Performance -- 4 Conclusion and Outlook -- References -- Improving Colon Carcinoma Grading by Advanced CNN Models -- 1 Introduction -- 2 Methods and Data -- 2.1 Advanced Deep Network Architectures -- 2.2 The Datasets: CRC and Extended CRC -- 3 Experimental Results on the Extended CRC Dataset -- 3.1 Comparisons to Leading Approaches in the Literature -- 4 Conclusion -- References -- Multimedia -- Frame Adaptive Rate Control Scheme for Video Compressive Sensing -- 1 Introduction -- 2 Proposed Frame Adaptive Rate Control Scheme -- 2.1 Overall System -- 2.2 Triangle Quantization for QP Initialization -- 2.3 Frame Adaptive QP Adjustment and Block-Based QP Refinement -- 3 Results and Comparison -- 3.1 Quantization Performance Comparison -- 3.2 Rate Control Performance Comparison -- 4 Conclusion -- References -- Shot-Based Hybrid Fusion for Movie Genre Classification -- 1 Introduction -- 2 Shot-Based Hybrid Fusion Networks -- 2.1 Video-Net -- 2.2 Audio-Net -- 2.3 Multi-modal Feature Fusion and Decision Fusion -- 3 Experiments and Results -- 3.1 Dataset and Data Preprocessing -- 3.2 Models Variations for Evaluation. ; 3.3 Experiment Settings and Evaluation Metrics -- 3.4 Results and Discussion -- 4 Conclusion -- References -- Landmark-Guided Conditional GANs for Face Aging -- 1 Introduction -- 2 Related Work -- 3 The Proposed Methods -- 3.1 Network Architecture -- 3.2 Objective Functions -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Qualitative Comparison -- 4.3 Quantitative Comparison -- 5 Conclusion -- References -- Introducing AV1 Codec-Level Video Steganography -- 1 Introduction -- 2 Related Works -- 3 Steganography on AV1 Codec-level -- 4 Experiments and Evaluation -- 4.1 Solution Capabilities -- 4.2 Visual Quality Preservation -- 4.3 Discussion -- 5 Conclusions and Future Works -- References -- Deep Learning -- Efficient Transfer Learning for Visual Tasks via Continuous Optimization of Prompts -- 1 Introduction -- 2 Methods -- 2.1 Pre-training -- 2.2 Fine-Tuning -- 2.3 Datasets -- 2.4 Training Procedure -- 3 Results -- 3.1 Classification -- 3.2 Few-Shot Classification -- 4 Discussion -- 4.1 Applications -- 4.2 Hyperparameters for VPT -- 4.3 Conclusion -- References -- Continual Learning with Neuron Activation Importance -- 1 Introduction -- 2 Proposed Method -- 2.1 Neuron Importance by Average Neuron Activation -- 2.2 Weight Re-initialization for Better Plasticity -- 3 Experimental Evaluations -- 3.1 MNIST -- 3.2 Split CIFAR10 -- 3.3 Split CIFAR10-100 -- 3.4 Split Tiny ImageNet -- 4 Conclusion -- References -- AD-CGAN: Contrastive Generative Adversarial Network for Anomaly Detection -- 1 Introduction -- 2 Related Work -- 3 Background -- 4 Proposed Approach -- 4.1 Contrastive GAN -- 4.2 Autoencoder -- 4.3 Latent Space Discriminator -- 4.4 Normality Score -- 5 Experimental Results -- 5.1 Datasets -- 5.2 Baseline Methods -- 5.3 Results -- 5.4 Ablation Study -- 6 Conclusion and Future Work -- References. ; Analyzing EEG Data with Machine and Deep Learning: A Benchmark.
• Titolo autorizzato: Image Analysis and Processing - ICIAP 2022
• ISBN: 3-031-06427-5
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910568298603321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture notes in computer science ; ; 13231.