Advances in Visual Computing : 18th International Symposium, ISVC 2023, Lake Tahoe, NV, USA, October 16-18, 2023, Proceedings, Part I

• Autore: Bebis George
• Pubblicazione: Cham : , : Springer, , 2024; ©2023
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (630 pages)
• Altri autori: GhiasiGolnaz FangYi SharfAndrei DongYue WeaverChris LeoZhicheng LaViola JrJoseph J KohliLuv
• Nota di contenuto: Intro -- Preface -- Organization -- Keynote Talks -- Machine Learning for Scientific Data Analysis and Visualization -- Estimating the Structure and Motion of Biomolecules at Atomic Resolutions -- Curriculum Learning and Active Learning, for Visual Object Recognition when Data is Scarce -- Have We Solved Image Correspondences? -- Visual Content Manipulation by Learning Generative Models -- Lights, Camera, Animation! Adaptive Simulation Methods for Training and Entertainment -- Beyond the Specs: A Computational and Human-Centered Approach to Wearability in AR/VR -- Contents - Part I -- Contents - Part II -- ST: Biomedical Image Analysis Techniques for Cancer Detection, Diagnosis and Management -- Hybrid Region and Pixel-Level Adaptive Loss for Mass Segmentation on Whole Mammography Images -- 1 Introduction -- 2 Related Work -- 2.1 Mass Segmentation on Whole Mammograms -- 2.2 Loss for Medical Image Segmentation -- 3 Methodology -- 3.1 Hybrid Pixel-Level Loss -- 3.2 Hybrid Region-Level Loss -- 3.3 Density-Adaptive Sample-Level Prioritizing Loss -- 4 Experimental Results -- 4.1 Datasets -- 4.2 Evaluation Metrics -- 4.3 Comparison with State-of-the-Art Methods -- 5 Conclusion -- References -- Deep Learning Based GABA Edited-MRS Signal Reconstruction -- 1 Introduction -- 2 Methods -- 2.1 Dataset -- 2.2 J-Difference Spectrum -- 2.3 Dual Branch Self-Attention Neural Network -- 2.4 Evaluation Metrics -- 3 Results and Discussion -- 4 Conclusion -- References -- Investigating the Impact of Attention on Mammogram Classification -- 1 Introduction -- 2 Data and Methods -- 2.1 Data Selection and Preprocessing -- 2.2 Selection of Models -- 2.3 Selection of Attention Methods -- 2.4 Training and Testing Process -- 3 Results and Discussion -- 3.1 Impact of Attention on CNN Performance -- 3.2 Impact of Model Architecture on Performance Differences. ; 3.3 Impact of Attention on Resolution -- 3.4 Impact of Attention on Abnormality Type -- 3.5 Relationship Between Model Activation and AU-ROC -- 4 Conclusions -- References -- ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation Using Object Border Fitting for Medical Images -- 1 Introduction -- 2 Our ReFit Framework -- 2.1 Unsupervised Segment Detection -- 2.2 Class Activation Map - CAM -- 2.3 The BoundaryFit Module -- 3 Results and Discussion -- 3.1 Ablation Studies -- 4 Conclusion -- References -- A Data-Centric Approach for Pectoral Muscle Deep Learning Segmentation Enhancements in Mammography Images -- 1 Introduction -- 2 Related Work -- 3 Mammography Segmentation -- 3.1 Dataset -- 3.2 Model Training -- 3.3 Drawbacks -- 4 Data-Centric Model Optimization -- 4.1 Stage I: Annotation Correction -- 4.2 Stage II: Downsampling -- 5 Results -- 5.1 Evaluation Metrics -- 5.2 Evaluated Training Datasets -- 5.3 Intersection over Union Evaluation -- 5.4 Classification Metrics for Pectoral Muscle Detection in CC View -- 6 Conclusion -- References -- Visualization -- Visualizing Multimodal Time Series at Scale -- 1 Introduction -- 2 Related Work -- 3 Overview Scenario -- 4 Detail Methods and Implementation -- 4.1 Time Series Dataset -- 4.2 Exploiting Elasticsearch for Fast Search and Big Query -- 4.3 Visualizing Time Series -- 5 Exploring UMAFall Dataset with TimeXplore -- 6 Conclusions and Future Work -- References -- Hybrid Tree Visualizations for Analysis of Gerrymandering -- 1 Introduction -- 2 Related Work -- 3 Gerrymandering -- 4 Data Model in Gerrymandering -- 5 Visual Design -- 6 Analysis Examples -- 6.1 Evaluating the Efficiency Gap -- 6.2 Assessing Electoral Competition -- 7 Conclusion -- References -- ArcheryVis: A Tool for Analyzing and Visualizing Archery Performance Data -- 1 Introduction -- 2 Related Work. ; 2.1 Archery Performance Analysis -- 2.2 Archery Scoring Apps -- 3 Data Collection, Processing, and Analysis -- 3.1 Data Collection -- 3.2 Ring and Center Detection -- 3.3 Shot Detection and Calibration -- 3.4 Scoring and Statistical Measures -- 4 Visual Interface and Interaction -- 5 Results and Discussion -- 5.1 Brushing and Filtering -- 5.2 Trainee Comparison -- 5.3 Statistical Measure as Performance Indicator -- 5.4 Empirical Evaluation -- 5.5 Limitations -- 6 Conclusions and Future Work -- References -- Spiro: Order-Preserving Visualization in High Performance Computing Monitoring -- 1 Introduction -- 2 Related Work -- 2.1 Spiral Layout in Visualization -- 2.2 Monitoring with Spiral Layout -- 3 Monitoring Tasks -- 4 Spiro Design -- 4.1 Design Rationales -- 4.2 Visual Encoding -- 5 Case Studies -- 5.1 Clustering on Compute Servers -- 5.2 Exploring Usage Behavior -- 6 Conclusion and Future Work -- References -- From Faces to Volumes - Measuring Volumetric Asymmetry in 3D Facial Palsy Scans -- 1 Introduction -- 2 Related Work -- 3 Data Acquisition -- 4 Methods -- 4.1 3D Landmark Extraction for Facial Palsy Patients -- 4.2 Radial Curves -- 4.3 Lateral Face Mesh Generation -- 4.4 Volume Estimation for Lateral Face Sides -- 4.5 Volumetric Difference Visualization -- 5 Volume Analysis During Dynamic Movements -- 6 Conclusions and Future Work -- References -- Video Analysis and Event Recognition -- Comparison of Autoencoder Models for Unsupervised Representation Learning of Skeleton Sequences -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Proposed Methods -- 4 Experiments -- 4.1 Datasets -- 4.2 Results Analysis and Comparisons -- 5 Conclusion and Future Works -- References -- Local and Global Context Reasoning for Spatio-Temporal Action Localization -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 3.1 Overall Pipeline. ; 3.2 Near-Actor Relation Network -- 4 Experiments on JHMDB21 -- 4.1 Implementation Details -- 4.2 Comparison on JHMDB21 -- 4.3 Ablation Study -- 4.4 Qualitative Results -- 5 Experiments on AVA -- 5.1 Implementation Details -- 5.2 Comparison on AVA -- 6 Conclusion -- References -- Zero-Shot Video Moment Retrieval Using BLIP-Based Models -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Computing Image and Text Embeddings -- 3.2 Sparse Frame-Sampling Strategies -- 3.3 Moment-Query Matching -- 4 Experiments -- 5 Results and Discussion -- 6 Conclusions and Future Work -- References -- Self-supervised Representation Learning for Fine Grained Human Hand Action Recognition in Industrial Assembly Lines -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Model Architecture -- 3.2 Masking Method -- 4 Experiments -- 4.1 Datasets -- 4.2 Model Training Environment -- 4.3 Self-supervised Pretraining and Downstream Task -- 5 Results and Analysis -- 5.1 Results Self-supervised Learning -- 5.2 Results Downstream Task -- 5.3 Analysis -- 6 Conclusion and Outlook -- References -- ST: Innovations in Computer Vision & -- Machine Learning for Critical & -- Civil Infrastructures -- Pretext Tasks in Bridge Defect Segmentation Within a ViT-Adapter Framework -- 1 Introduction -- 2 Methods -- 2.1 ViT-Adapter Model -- 2.2 Datasets -- 2.3 Supervised Learning (SL) Pre-training -- 2.4 Self- And Semi-Supervised Learning (SSL) Pre-training -- 2.5 Training Parameters -- 3 Results and Discussion -- 4 Conclusion -- References -- A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation -- 1 Introduction -- 1.1 Current Limitations and Our Contribution -- 2 Proposed Architecture -- 2.1 R2AU-Net Architecture for Road Crack Segmentation -- 2.2 Few-Shot Learning for Segmentation Refinement -- 3 Experimental Setup and Results -- 3.1 Dataset Description. ; 3.2 Comparative Algorithms and Training Configuration -- 3.3 Experiments and Comparisons -- 4 Conclusions -- References -- Efficient Resource Provisioning in Critical Infrastructures Based on Multi-Agent Rollout Enabled by Deep Q-Learning -- 1 Introduction -- 2 Related Work -- 3 Workload Management in Critical Infrastructures -- 3.1 Infrastructure Model -- 3.2 Problem Formulation -- 3.3 Deterministic Markov Decision Process Model -- 3.4 Multi-Agent Rollout Enabled by Deep Q-Learning -- 4 Simulation Experiments -- 4.1 Experimental Setup -- 4.2 Evaluation Results -- 5 Conclusions -- References -- Video-Based Recognition of Aquatic Invasive Species Larvae Using Attention-LSTM Transformer -- 1 Introduction -- 1.1 Attention-LSTM -- 2 Related Work -- 3 Proposed Method -- 3.1 Model Architecture -- 3.2 Attention-LSTM Layer -- 3.3 Model Variations -- 4 Invasive Species Dataset -- 5 Empirical Evaluation -- 6 Conclusion -- References -- ST: Generalization in Visual Machine Learning -- Latent Space Navigation for Face Privacy: A Case Study on the MNIST Dataset -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 4 Experimental Result -- 5 Future Work -- 6 Conclusion -- References -- Domain Generalization for Foreground Segmentation Using Federated Learning -- 1 Introduction -- 2 Related Work -- 3 Proposed Work -- 3.1 Model Architecture -- 3.2 Training Technique -- 4 Experiments -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Traditional Foreground Segmentation Experiment -- 4.4 Domain Generalization Experiment -- 4.5 Few-Shot Experiment -- 5 Conclusion and Future Work -- References -- Probabilistic Local Equivalence Certification for Robustness Evaluation -- 1 Introduction -- 2 Related Work -- 3 Probabilistic Local Equivalence Certification -- 3.1 Probabilistic Local Equivalence Certification -- 3.2 When Labels are Available. ; 3.3 The Case of Classification.
• Titolo autorizzato: Advances in Visual Computing
• ISBN: 3-031-47969-6
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996565867203316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Computer Science Series