top

  Info

  • Utilizzare la checkbox di selezione a fianco di ciascun documento per attivare le funzionalità di stampa, invio email, download nei formati disponibili del (i) record.

  Info

  • Utilizzare questo link per rimuovere la selezione effettuata.

Biblioteca

MARC Lista (tabellare)
2021 international conference on applications and techniques in cyber intelligence Applications and techniques in cyber intelligence (ATCI 2021) . Volume 2 / / Jemal Abawajy [and three others], editors
2021 international conference on applications and techniques in cyber intelligence Applications and techniques in cyber intelligence (ATCI 2021) . Volume 2 / / Jemal Abawajy [and three others], editors
Pubbl/distr/stampa Cham, Switzerland : , : Springer, , [2021]
Descrizione fisica 1 online resource (943 pages)
Disciplina 006.3
Collana Lecture Notes on Data Engineering and Communications Technologies
Soggetto topico Computational intelligence
Robòtica
Processament de dades
Intel·ligència computacional
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 3-030-79197-1
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Record Nr. UNINA-9910495225803321
Cham, Switzerland : , : Springer, , [2021]
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing in Bioinformatics : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part I / / edited by De-Shuang Huang, Qinhu Zhang, Jiayang Guo
Advanced Intelligent Computing in Bioinformatics : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part I / / edited by De-Shuang Huang, Qinhu Zhang, Jiayang Guo
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (490 pages)
Disciplina 572.80285
Collana Lecture Notes in Bioinformatics
Soggetto topico Computational intelligence
Artificial intelligence
Bioinformatics
Computational Intelligence
Artificial Intelligence
Computational and Systems Biology
Bioinformàtica
Intel·ligència computacional
Intel·ligència artificial
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-89-8
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Biomedical Data Modeling and Mining -- Alzheimer's Disease Diagnosis via Specific-Shared Representation Learning in Multimodal Neuroimaging -- 1 Introduction -- 2 Method -- 2.1 Overview -- 2.2 Shallow Feature Learning -- 2.3 Modality Specific Representation Learning -- 2.4 Modality Shared Representation Learning -- 2.5 Modality Specific-Shared Representation Learning -- 3 Experiments -- 3.1 Materials and Image Pre-processing -- 3.2 Comparison Methods -- 3.3 Experimental Setup -- 3.4 Evaluation of Automated Diseases Diagnosis -- 3.5 Ablation Study -- 4 Conclusion -- References -- An Activity Graph-Based Deep Convolutional Neural Network Framework in Symptom Severity Diagnosis Towards Parkinson's Disease Using Inertial Sensors -- 1 Introduction -- 2 Subjects and Data Collection -- 2.1 Participants -- 2.2 Data Collection -- 3 Methodology -- 3.1 Activity Graph Generation -- 3.2 Data Augmentation -- 3.3 Convolutional Neural Network -- 4 Results -- 5 Discussion and Conclusion -- References -- An Optimization Method for Drug Design Based on Molecular Features -- 1 Introduction -- 2 Methods -- 2.1 Pocket of Targeted Protein -- 2.2 Feature Extraction of Targeted Protein -- 2.3 Feature Representation of Drug Molecule -- 2.4 Model -- 3 Experimental Results -- 3.1 Datasets -- 3.2 Comparison of Experiments -- 4 Conclusion -- References -- Application of Machine Learning and Large Language Model Module for Analyzing Gut Microbiota Data -- 1 Introduction -- 2 Methodology -- 2.1 Overview -- 2.2 Machine Learning Algorithms -- 2.3 Chat2GM - a LLM Module Based on Langchain Framework -- 3 Applications and Analysis -- 3.1 Data -- 3.2 Species Diversity Analysis with Statistical Methods -- 3.3 Identification of Obesity-Related Biomarkers via Machine Learning.
3.4 Gut Microbiota Data Analysis with Chat2GM Module -- 4 Conclusions -- References -- CVAE-Based Hybrid Sampling Data Augmentation Method and Interpretation for Imbalanced Classification of Gout Disease -- 1 Introduction -- 2 Materials and Methods -- 2.1 CVAE-Based Hybrid Sampling -- 2.2 Detection Model -- 2.3 Interpretation -- 3 Experiment and Result -- 3.1 Datasets -- 3.2 Classification Results -- 3.3 Comparison of Balancing Strategies -- 3.4 Model Interpretation -- 4 Conclusion -- References -- DepthParkNet: A 3D Convolutional Neural Network with Depth-Aware Coordinate Attention for PET-Based Parkinson's Disease Diagnosis -- 1 Introduction -- 2 Method -- 2.1 Depth-Aware Coordinate Attention -- 2.2 PDaug -- 2.3 Class-Balanced Loss -- 3 Experiments -- 3.1 Datasets and Preprocessing -- 3.2 Implementation Details -- 3.3 Comparison -- 3.4 Ablation Study -- 4 Conclusion -- References -- Gene Selection and Classification Method Based on SNR and Multi-loops BPSO -- 1 Introduction -- 2 Method -- 2.1 The Multi-loops BPSO -- 3 Experiments and Results -- 3.1 Experiment Preparation -- 3.2 Experimental Design Principles -- 3.3 Preprocessing by SNR -- 3.4 The Comparison of One-Loop and Multi-loops on BPSO -- 3.5 Comparative Experiment and Analysis -- 4 Conclusion -- References -- Graph Convolutional Networks Based Multi-modal Data Integration for Breast Cancer Survival Prediction -- 1 Introduction -- 2 Method -- 2.1 Feature Selection and Fusion -- 2.2 Patient-Patient Graph Construction -- 2.3 Multi-modal Graph Convolutional Networks Module -- 2.4 Training Details -- 3 Experiments -- 3.1 Datasets and Evaluation Metrics -- 3.2 Comparisons with State-of-The-Art -- 3.3 Ablation Studies -- 3.4 Validation -- 4 Conclusion and Future Work -- References -- IDHPre: Intradialytic Hypotension Prediction Model Based on Fully Observed Features -- 1 Introduction.
2 Related Work -- 2.1 Imputation of Missing Values -- 2.2 Feature Selection -- 3 IDHPre -- 3.1 Imputation of Missing Values -- 3.2 Feature Selection -- 4 Experiment and Evaluation -- 4.1 Implementation Details -- 4.2 Qualitative and Quantitative Comparison -- 4.3 Ablation Study -- 5 Conclusion -- References -- Machine Learning Models for Improved Cell Screening -- 1 Introduction -- 2 Related Work -- 2.1 Mainstream Cell Line Screening Methods -- 2.2 Model Stacking -- 3 Dataset -- 4 Proposed Methods -- 4.1 Stacked Machine Learning Method (SMLM) -- 4.2 Simple Linear Method (SLM) -- 4.3 Model Characteristics and Applicability Analysis -- 5 Experimental Results -- 5.1 Experimental Setup -- 5.2 Experimental Analysis -- 6 Conclusion and Pen Question -- References -- Prediction of Bladder Cancer Prognosis by Deep Cox Proportional Hazards Model Based on Adversarial Autoencoder -- 1 Introduction -- 2 Methods -- 2.1 The Framework of the Study -- 2.2 Adversarial Autoencoders -- 2.3 The Architecture of AAE-Cox -- 3 Results -- 3.1 Datasets -- 3.2 Experiments -- 3.3 Evaluations of Cancer Outcomes Prediction -- 3.4 Method Comparison -- 3.5 Independent Test -- 3.6 Identification of Cancer-Related Prognostic Markers and Pathways -- 4 Conclusion and Discussion -- References -- SGEGCAE: A Sparse Gating Enhanced Graph Convolutional Autoencoder for Multi-omics Data Integration and Classification -- 1 Introduction -- 2 Methods -- 2.1 Overview of SGEGCAE -- 2.2 AE for Attribute Information Representation -- 2.3 EGCAE for Feature Representations -- 2.4 Sparse Gating Strategy for Enhanced Feature Representations -- 2.5 TCP for Omics Informativeness Estimation -- 2.6 TFN for Multi-omics Integration -- 3 Experiments and Results -- 3.1 Datasets and Evaluation Metrics -- 3.2 Analysis of Classification Results -- 3.3 Ablation Studies -- 3.4 Analysis of Hyper-parameter.
3.5 Analysis of Different Omics Data Types -- 4 Conclusion -- References -- Short-Term Blood Glucose Prediction Method Based on Signal Decomposition and Bidirectional Networks -- 1 Introduction -- 2 Short-Term Blood Glucose Prediction Method Based on Signal Decomposition and Bidirectional Networks -- 2.1 Overall Approach -- 2.2 Variation Mode Decomposition Algorithm Based on Sparrow Search -- 2.3 Composite Network of Bidirectional Gated Recurrent Unit (BiGRU) and Bidirectional Long Short-Term Memory (BiLSTM) -- 3 Results and Analysis -- 3.1 Experimental Environment and Parameter Settings -- 3.2 Model Performance Evaluation Metrics -- 3.3 Model Performance Evaluation Metrics -- 4 Conclusion -- References -- SLGNNCT: Synthetic Lethality Prediction Based on Knowledge Graph for Different Cancers Types -- 1 Introduction -- 2 Dataset -- 3 Method -- 3.1 Knowledge Graph Level Gene Embedding Generation -- 3.2 Message Aggregation Based on Factors -- 3.3 Calculation of Synthetic Lethal Interaction Probabilities -- 4 Experiment -- 4.1 Baselines -- 4.2 Model Evaluation -- 4.3 Results and Analysis of Ablation Experiments -- 5 Conclusion -- References -- TransPBMIL: Transformer-Based Weakly Supervised Prognostic Prediction in Ovarian Cancer with Pseudo-Bag Strategy -- 1 Introduction -- 2 Materials and Methods -- 2.1 Participants and Dataset Generation -- 2.2 TransPBMIL Framework -- 3 Result -- 3.1 Comparison with Existing Weakly Supervised Works -- 3.2 The Performance Improvement Brought by the Pseudo-Bag Strategy. -- 3.3 Visualization of Detection Results -- 4 Conclusion -- References -- Biomedical Informatics Theory and Methods -- A Heterogeneous Cross Contrastive Learning Method for Drug-Target Interaction Prediction -- 1 Introduction -- 2 Method -- 2.1 Graph Embedding Module -- 2.2 Self-contrast Module -- 2.3 Cross-Contrast Module.
2.4 Pairwise Judgment Module -- 3 Experiments -- 3.1 Datasets -- 3.2 Experimental Settings -- 3.3 Experimental Results. -- 3.4 Parameter Sensitivity Analysis. -- 4 Conclusion -- References -- A Retrieval-Based Molecular Style Transformation Optimization Model -- 1 Introduction -- 2 Methods -- 2.1 Overview -- 2.2 Molecular Retriever -- 2.3 Information Fusion Module and Decoder -- 2.4 Retrieval-Based Molecular Style Transformation Generative Network -- 3 Results -- 3.1 Datasets and Performance Metrics -- 3.2 Results on the QED and PlogP Tasks -- 3.3 Ablation Experiments -- 3.4 Visualized Optimization Results -- 3.5 Parameter Analysis -- 4 Conclusion -- References -- Aggregation Strategy with Gradient Projection for Federated Learning in Diagnosis -- 1 Introduction -- 2 Method -- 2.1 Problem Definition -- 2.2 Federal Projection Matrix -- 2.3 Local Training with GPM -- 3 Experiment -- 3.1 Datasets and Experiment Settings -- 3.2 Implementation Details -- 3.3 Evaluation and Discussion -- 3.4 Ablation Studies -- 4 Conclusion -- References -- Coronary Artery 3D/2D Registration Based on Particle Swarm Optimization of Contextual Morphological Features -- 1 Introduction -- 2 Proposed Method -- 2.1 DSA Vessel Intersection Extraction -- 2.2 CTA Vessel Intersection Extraction -- 2.3 3D-2D Vessel Matching Based on PSO -- 3 Experiments and Results -- 3.1 DSA Vessel Intersection Extraction Results -- 3.2 Results of CTA Vascular Center Line and Intersection -- 3.3 Results of Vascular Matching Between CTA and DSA -- 4 Conclusions -- References -- Enhancing Drug-Drug Interaction Predictions in Biomedical Knowledge Graphs Through Integration of Householder Projections and Capsule Network Techniques -- 1 Introduction -- 2 Preliminaries -- 2.1 Projective Space -- 2.2 Advanced Formulation of Householder Projections -- 3 Model -- 3.1 Relational Householder Projections.
3.2 Möbius Representation Transformation.
Record Nr. UNINA-9910878049003321
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing in Bioinformatics : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part II / / edited by De-Shuang Huang, Yijie Pan, Qinhu Zhang
Advanced Intelligent Computing in Bioinformatics : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part II / / edited by De-Shuang Huang, Yijie Pan, Qinhu Zhang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (505 pages)
Disciplina 572.80285
Collana Lecture Notes in Bioinformatics
Soggetto topico Computational intelligence
Artificial intelligence
Bioinformatics
Computational Intelligence
Artificial Intelligence
Computational and Systems Biology
Bioinformàtica
Intel·ligència artificial
Intel·ligència computacional
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-92-8
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part II -- Contents - Part I -- Biomedical Data Modeling and Mining -- AAHLDMA: Predicting Drug-Microbe Associations Based on Bridge Graph Learning -- 1 Introduction -- 2 Materials -- 2.1 Drug Similarity Attribute -- 2.2 Drug Network Topological Attribute -- 2.3 Fused Drug Attribute -- 2.4 Microbe Functional Similarity Attribute -- 2.5 Microbe Sequence Attribute -- 2.6 Fused Microbe Attribute -- 3 Methods -- 3.1 Attention-Based Graph Autoencoder -- 3.2 Construction of Bridge Graph -- 3.3 Classification -- 4 Experiment -- 4.1 Experimental Setup -- 4.2 Model Performance -- 4.3 Performance Comparison with Other Models -- 4.4 Case Study -- 5 Conclusion -- References -- Adaptive Weight Sampling and Graph Transformer Neural Network Framework for Cell Type Annotation of Scrna-seq Data -- 1 Introduction -- 2 Materials -- 2.1 scRNA-seq Datasets -- 2.2 Gene Interaction Networks -- 3 Methods -- 3.1 Adaptive Sampling -- 3.2 Graph Representation Module -- 4 Experimental Results -- 4.1 Model ACC Performance -- 4.2 Model ACC Performance -- 4.3 Sankey Diagram Representation of the Model on the Data Set -- 5 Conclusion -- References -- BiLETCR: An Efficient PMHC-TCR Combined Forecasting Method -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 BiLETCR Model Structure and Forecasting Process -- 3.2 EMA -- 3.3 Model Training -- 4 Experiments -- 4.1 Data Collection and Processing -- 4.2 Experimental Design -- 4.3 Adding EMA Module Can Improve the Performance of the Model -- 4.4 For the Generalization Test of BiLETCR, the Prediction Effect of BiLETCR is Better Than the Existing Model -- 4.5 BiLETCR is Superior to the Existing Model in Computational Efficiency -- 4.6 BiLETCR is Superior to the Existing Prediction Tools on Ts-Special Test Set -- 5 Conclusion -- References.
CDDTR: Cross-Domain Autoencoders for Predicting Cell Type Specific Drug-Induced Transcriptional Responses -- 1 Introduction -- 2 Materials and Methods -- 2.1 Within-Domain Reconstruction Paths -- 2.2 Cross-Domain Reconstruction Paths -- 2.3 Training and Prediction Procedures -- 2.4 Comparison with Alternative Methods -- 3 Results -- 3.1 Comparison Results with the State-of-the-Art Methods -- 3.2 The Performance of CDDTR on Small Sample Data -- 3.3 Biological Interpretability of CDDTR Model -- 3.4 Further Improvement of Prediction Performance of CDDTR -- 3.5 Case Study -- 4 Conclusion and Discussion -- References -- ChiMamba: Predicting Chromatin Interactions Based on Mamba -- 1 Introduction -- 2 Materials and Methods -- 2.1 Datasets and Processing -- 2.2 Selective State Space Models -- 2.3 ChiMamba Model -- 3 Experiment -- 3.1 Datasets and Experiment Setup -- 3.2 Comparative Studies -- 3.3 Ablation Studies -- 3.4 Training Time -- 4 Discussion -- References -- Cluster Analysis of Scrna-Seq Data Combining Bioinformatics with Graph Attention Autoencoders and Ensemble Clustering -- 1 Introduction -- 2 Materials -- 2.1 Dataset -- 2.2 Processing Gene Expression Matrix -- 2.3 Denoising Using Network Enhancement -- 2.4 Performing Principal Component Analysis -- 3 Methods -- 3.1 Graph Attention Autoencoder -- 3.2 Bipartite Graph Ensemble Clustering Method -- 4 Experimental Results -- 4.1 Model Performance -- 4.2 Comparison of Different Model -- 4.3 Comparison of Different Datasets -- 5 Conclusion -- References -- Compound-Protein Interaction Prediction with Sparse Perturbation-Aware Attention -- 1 Introduction -- 2 Methodology -- 2.1 Prediction Backbone -- 2.2 Perturbation-Aware Attention -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Implementation Details -- 3.3 Comparative Performance -- 3.4 Impacts of Modules and Parameters -- 3.5 Case Study.
4 Related Work -- 5 Conclusion -- References -- CUK-Band: A CUDA-Based Multiple Genomic Sequence Alignment on GPU -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 The Strategy of Affine Gap Penalty and K-band -- 3.2 Improved Central Star Strategy Based on Bitmap -- 3.3 The K-band Strategy Based on CUDA -- 4 Performance Evaluation -- 4.1 Datasets and Evaluation Criterion -- 4.2 Configuration -- 4.3 Results -- 5 Conclusion -- References -- DeepMHAttGRU-DTI: Prediction of Drug-Target Interactions Based on Knowledge Graph Random Walk Embeddings and GRU Neural Network -- 1 Introduction -- 2 Materials and Methods -- 2.1 Graph Embedding Algorithm Based on Three Improved Random Walk Algorithms -- 2.2 GRU Binary Classification Neural Network Model -- 2.3 Multi-head Attention -- 3 Experimental Results -- 3.1 Evaluation Criteria -- 3.2 General Dataset -- 3.3 Comparison of Different Random Walk Algorithms Using GRU Model -- 3.4 Comparison Between the GRU Model and the MHAttGRU Model -- 3.5 Comparison with Other Existing Models -- 4 Conclusion -- References -- DiagNCF: Diagnosis Neural Collaborative Filtering for Accurate Medical Recommendation -- 1 Introduction -- 2 Preliminaries -- 2.1 Setup and Notation -- 2.2 Data-Preprocessing -- 3 Diagnose Neural Collaborative Filtering (DiagNCF) -- 3.1 General Framework -- 3.2 Generalized Matrix Factorization (GMF) -- 3.3 Multi-Layer Perception (MLP) -- 3.4 DiagNCF -- 4 Experiments -- 4.1 Performance Evaluation -- 4.2 Training Procedure -- 5 Conclusions -- References -- Drug Molecule Generation Method Based on Fusion of Protein Sequence Features -- 1 Introduction -- 2 Methods -- 2.1 Datasets -- 2.2 Targeted Drug Generation Process -- 3 Experimental Results -- 3.1 Evaluation of Model Performance -- 3.2 Molecular Docking Results -- 4 Conclusion -- References.
Drug Target Affinity Prediction Based on Graph Structural Enhancement and Multi-scale Topological Feature Fusion -- 1 Introduction -- 2 Methods -- 2.1 Model Architecture -- 2.2 Drug Feature Extraction Module -- 2.3 Protein Feature Extraction Module -- 2.4 Multi-scale Topological Feature Fusion Module -- 3 Results and Discussion -- 3.1 Datasets -- 3.2 Evaluation Metrics -- 3.3 Parameters Setting -- 3.4 Performance Comparison with Baseline Model -- 4 Ablation Experiment -- 5 Conclusion -- References -- Drug-Target Interaction Prediction Based on Multi-path Graph Convolution and Graph-Level Attention Mechanism -- 1 Introduction -- 2 Methods -- 2.1 Method Overview -- 2.2 Feature Extraction -- 2.3 Multi-feature Graph Convolution Module -- 2.4 Loss Function -- 3 Results -- 3.1 Dataset -- 3.2 Experiment Settings -- 3.3 Comparisons with Other Baseline Methods -- 3.4 Ablation Experiments -- 3.5 Model Generalization Test -- 4 Conclusion -- References -- Fully Convolutional Neural Network for Predicting Cancer-Specific CircRNA-MiRNA Interaction Sites -- 1 Introduction -- 2 Materials and Methods -- 2.1 Data -- 2.2 Modelling -- 3 Results -- 4 Discussion and Conclusion -- References -- GSDPI: An Integrated Feature Extraction Framework for Predicting Novel Drug-Protein Interaction -- 1 Introduction -- 2 Materials and Methods -- 2.1 Datasets -- 2.2 Low-Dimensional Feature Vectors and Feature Similarity Matrices -- 2.3 Determining the Dimensionality of Feature Matrix -- 2.4 Calculation of the Feature Similarity Matrices -- 2.5 DPI Prediction Model Based on GSDPI -- 3 Experimental Evaluation -- 3.1 Evaluation Metrics -- 3.2 Method Comparison and Parameter Settings -- 3.3 Experimental Comparison -- 3.4 Ablation Experiments -- 3.5 Integrate the Gene Ontology (GO) Annotation for All Drug Target-Coding Genes -- 3.6 Case Study -- 4 Conclusion -- References.
Heterogeneous Genome Compression on Mobile Devices -- 1 Introduction -- 2 Related Works -- 2.1 Genome Data Compression -- 2.2 Hardware Accelerated Bioinformatics -- 3 Background -- 3.1 Heterogeneity of MPSoC -- 3.2 Dynamic Voltage-Frequency Scaling -- 4 Methods -- 4.1 Distribute Tasks Transparently -- 4.2 Pipeline Organization -- 5 Results and Discussions -- 5.1 Test Data -- 5.2 Performance and Energy Efficiency Improvements of Heterogeneous Gzip -- 5.3 Exploration for the Reason of Extra Energy Consumption and Discussion -- 6 Conclusion -- References -- HyperCPI: A Novel Method Based on Hypergraph for Compound Protein Interaction Prediction with Good Generalization Ability -- 1 Introduction -- 2 Materials and Methods -- 2.1 Datasets -- 2.2 Hypergraphs -- 2.3 Model Architecture of HyperCPI -- 3 Results and Discussion -- 3.1 Performance on OOD Experiments -- 3.2 Ablation Study -- 4 Conclusion -- References -- iEMNN: An Iterative Integration Method for Single-Cell Transcriptomic Data Based on Network Similarity Enhancement and Mutual Nearest Neighbors -- 1 Introduction -- 2 Materials and Methods -- 2.1 Overview of iEMNN -- 2.2 Network Similarity Enhancement -- 2.3 Methods for Comparison -- 2.4 Performance Metrics -- 3 Results -- 3.1 iEMNN Enhances the Similarity of Similar Cells While Separating Distinct Cells -- 3.2 Scenario 1: iEMNN in the Scenario of Identical Cell Types -- 3.3 Scenario 2: iEMNN in the Scenario of Non-identical Cell Types -- 3.4 Scenario 3: iEMNN in the Scenario of Multiple Batches -- 3.5 Scenario 4: iEMNN in the Scenario of Cross-Species -- 4 Discussion -- References -- IGDACA: Imaging Genomics of Deep Autoencoder Cascade Attention Fusion Networks for Cervical Cancer Prognosis Prediction -- 1 Introduction -- 2 Method -- 2.1 Model Design -- 2.2 Image Feature Extraction -- 2.3 Gene Feature Extraction -- 2.4 Attention Fusion Module.
3 Experiments and Analyses.
Record Nr. UNINA-9910878052503321
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part XII / / edited by De-Shuang Huang, Yijie Pan, Jiayang Guo
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part XII / / edited by De-Shuang Huang, Yijie Pan, Jiayang Guo
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (536 pages)
Disciplina 006.3
Collana Lecture Notes in Computer Science
Soggetto topico Computational intelligence
Machine learning
Computer networks
Application software
Computational Intelligence
Machine Learning
Computer Communication Networks
Computer and Information Systems Applications
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 9789819756155
9789819756148
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part XII -- Intelligent Computing in Computer Vision -- A 6-DoF Grasping Network Using Feature Augmentation for Novel Domain Generalization -- 1 Introduction -- 2 Methodology -- 2.1 Gaussian Noise Mix -- 2.2 Resblock Module -- 2.3 Local Features Interpolation -- 3 Experiments -- 3.1 Comparison with the State-of-the-Art -- 3.2 Generalization Analysis of Novel Domain -- 3.3 Visualization -- 3.4 Ablation Study -- 3.5 Practical Evaluation -- 4 Conclusion -- References -- TC-YOLO: Enhanced Vehicle Detection Approach for Traffic Surveillance Cameras Based on YOLOv8 -- 1 Introduction -- 2 Related Works -- 3 Method -- 3.1 Network Structure -- 3.2 Deformable Convolution for Enhancing Spatial Deformation Adaptability -- 3.3 Global Attention is Used to Enhance Cross-Dimensional Interaction Features -- 3.4 An Enhanced Detecting Head -- 4 Experiments -- 4.1 Experimental Dataset -- 4.2 Experimental Environment and Configuration -- 4.3 Evaluation Metrics -- 4.4 Algorithm Comparison -- 4.5 Ablation Study -- 5 Conclusion -- References -- MineDet: A Real-Time Object Detection Framework Based Neural Architecture Search for Coal Mines -- 1 Introduction -- 2 Related Work -- 2.1 Object Detection Based on NAS -- 2.2 Lightweight Model Design -- 3 Method -- 3.1 The Reparameterization Technique -- 3.2 Efficient Search Space -- 3.3 Search Algorithm -- 4 Experimental -- 4.1 Dataset and Implementation Details -- 4.2 Experimental Results -- 5 Conclusion -- References -- Multi-gait Synthesis Based on Convolutional Neural Networks -- 1 Introduction -- 2 Related Work -- 2.1 Multi-gait Dataset -- 2.2 2D and 3D Convolution -- 2.3 Image Synthesis -- 2.4 Encoder and Decoder -- 2.5 Gait Recognition -- 3 Method -- 3.1 CNN Block -- 3.2 Encoder -- 3.3 Feature Merging -- 3.4 Decoder -- 3.5 Optimization Strategy -- 4 Experiment.
4.1 Datasets -- 4.2 Single Frame and Multi Frame -- 4.3 Gait Recognition and Similarity Comparison -- 5 Summary -- References -- Controlling Attention Map Better for Text-Guided Image Editing Diffusion Models -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 3.1 Diffusion Models -- 3.2 Inversion Methods -- 3.3 Attention Control Methods -- 4 Methodology -- 4.1 Motivation -- 4.2 Integrate Attention Control -- 5 Experiments -- 5.1 Benchmark -- 5.2 Implementation Details -- 5.3 Results -- 5.4 Ablation Study -- 6 Conclusion and Future Work -- References -- Spatial Group and Cross-Channel Attention: Make Smaller Models More Effective, Focus on High-Level Semantic Features -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Spatial Group and Cross-Channel Attention -- 3.2 Visualization and Interpretation -- 4 Experiments on Image Classification -- 4.1 Implementation Details -- 4.2 Image Classification -- 4.3 Parameter Experiment -- 5 Conclusion -- References -- YOLO-BS: A Better Object Detection Model for Real-Time Driver Behavior Detection -- 1 Introduction -- 2 Method -- 2.1 EVITS Module -- 2.2 ASPPMP Module -- 3 Experiments -- 3.1 Implementation Details -- 3.2 Datasets -- 3.3 Experimental Results -- 4 Conclusion -- References -- Fusion Attention Graph Convolutional Network with Hyperskeleton for UAV Action Recognition -- 1 Introduction -- 2 Proposed FA-GCN Method -- 2.1 The Network Architecture -- 2.2 Spatiotemporal Channel Fusion Attention Mechanism -- 2.3 Hyperskeleton Features -- 2.4 Gaussian Center Enhanced Interpolation Strategy -- 3 Experiments -- 3.1 Datasets and Experimental Setup Details -- 3.2 Ablation Studies and Comparative Analysis -- 3.3 Comparison with the State-of-the-Art -- 4 Conclusion -- References -- Enhancing Adversarial Robustness for Deep Metric Learning via Attention-Aware Knowledge Guidance -- 1 Introduction.
2 Related Work -- 3 Proposed Method -- 3.1 Preliminaries -- 3.2 Adversarial Attention-Aware Knowledge Guidance -- 3.3 Benign Attention-Aware Knowledge Guidance -- 3.4 Optimization -- 4 Experiments -- 4.1 Experiment Setup -- 4.2 Detailed Robustness Evaluation -- 5 Ablation and Discussions -- 5.1 Loss Function -- 5.2 Training Interval -- 5.3 Weak Robustness Subnet Width -- 5.4 Attention-Aware Knowledge Guidance -- 6 Conclusion -- References -- IMFA-Stereo: Domain Generalized Stereo Matching via Iterative Multimodal Feature Aggregation Cost Volume -- 1 Introduction -- 2 Related Work -- 2.1 Cost Filtering-Based Methods -- 2.2 Iterative Methods -- 3 Method -- 3.1 Multi-scale Feature Extractor -- 3.2 Initial Disparity Estimation -- 3.3 Aggregated Cost Volume -- 3.4 ConvGRU-Based Updater -- 3.5 Loss Function -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Ablation Study -- 4.3 Comparisons with State-of-the-Art -- 4.4 Cross-Domain Generalization -- 5 Conclusion -- References -- Anomaly Behavior Detection in Crowd via Lightweight 3D Convolution -- 1 Introduction -- 2 Method -- 2.1 Overall Framework -- 2.2 Channel-Only Polarized Self-attention -- 2.3 3D Separable Convolution -- 2.4 Truncated Singular Value Decomposition -- 3 Experiments and Analysis -- 3.1 Experimental Datasets and Preparation -- 3.2 Evaluation on Hajjv2 -- 3.3 Ablation Study -- 3.4 Validation on Benchmarks -- 3.5 Parameter Comparison and Results -- 4 Conclusion -- References -- Generating Graph-Based Rules for Enhancing Logical Reasoning -- 1 Introduction -- 2 Related Work -- 2.1 GNNs on Knowledge Graphs -- 2.2 Logical Rule Mining -- 3 Preliminary -- 4 Method -- 4.1 Graph-Based Rule Generator (GRG) -- 4.2 Subgraph Reasoning Module (SRM) -- 4.3 Loss Function -- 5 Experiments -- 5.1 Experiment Setup -- 5.2 Comparisons with Other Approaches -- 5.3 Ablation Studies.
5.4 Hyperparamter Analysis -- 5.5 Visualization Experiments -- 6 Conclusions -- References -- YOLO-PR: Multi Pose Object Detection Method for Underground Coal Mine -- 1 Introduction -- 2 Related Work -- 3 The Proposed Method -- 3.1 Backbone Network Incorporating EPA Modules -- 3.2 Neck Network Integrating RFB Modules -- 3.3 Loss Function Based on PioU V2 -- 4 Experiments -- 4.1 Datasets and Evaluation Indicators -- 4.2 Result Analysis and Ablation Experiment -- 5 Conclusion -- References -- DSMENet: A Road Segmentation Network Based on Dual-Branch Dynamic Snake Convolutional Encoding and Multi-modal Information Iterative Enhancement -- 1 Introduction -- 2 Method -- 2.1 Overall Architecture -- 3 Dynamic Snake Convolution -- 3.1 Multi-modal Feature Fusion Module -- 3.2 Multi-modal Information Iterative Enhancement Module -- 4 Experiment -- 4.1 Datasets and Experimental Setup -- 4.2 Comparative Experiments -- 4.3 Ablation Study -- 5 Conclusion -- References -- MPRNet: Multi-scale Pointwise Regression Network for Crowd Counting and Localization -- 1 Introduction -- 2 Related Works -- 3 Proposed Approach -- 3.1 Overall Counting and Localization Workflow -- 3.2 Multi-Scale Feature Extractor -- 3.3 Regional Maximum Substitution -- 3.4 One-to-One Points Matching -- 3.5 Training Objective -- 4 Experiment -- 4.1 Datasets and Configurations -- 4.2 Evaluation Metrics and Results -- 4.3 Ablation Studies -- 5 Conclusion -- References -- Text-to-Image Generation with Multiscale Semantic Context-Aware Generative Adversarial Networks -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Model Overview -- 3.2 Semantic Adaptive Affine Fusion -- 3.3 CrossBlock Context Aware Encoding -- 3.4 Objective Function -- 4 Experiment -- 4.1 Quantitative Results -- 4.2 Qualitative Results -- 4.3 Ablation Studies -- 5 Future Work -- 6 Conclusion -- References.
CHMF: Colorful Human Reconstruction Based on Mesh Features -- 1 Introduction -- 2 Related Work -- 2.1 3D Human Color Estimation -- 2.2 3D Object Features Extraction -- 3 Method -- 3.1 Color Features Extraction and Mapping -- 3.2 Structural Features Extraction and Color Features Repair -- 3.3 Shape Features Extraction and Transformation -- 3.4 Features Decoding and Loss Functions -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Qualitative and Quantitative Comparisons -- 4.3 Ablation Study -- 4.4 Limitations -- 5 Conclusion -- References -- Face Swapping via Reverse Contrastive Learning and Explicit Identity-Attribute Disentanglement -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Reverse Contrastive Learning -- 3.2 Information Disentanglement -- 3.3 Loss Functions -- 4 Experiments -- 4.1 Experience Details -- 4.2 Comparison with Other Methods -- 4.3 Analysis of RCLSwap -- 5 Conclusion -- References -- OSFENet: Object Spatiotemporal Feature Enhanced Network for Surgical Phase Recognition -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Surgical Tool Alignment -- 3.2 Spatial Feature Encoder -- 3.3 Object Spatial Feature Enhanced Module -- 3.4 Object Temporal Feature Enhanced Module -- 3.5 Fusion Module -- 3.6 Loss Function -- 4 Experiments -- 4.1 Dataset -- 4.2 Experimental Settings -- 4.3 Online Surgical Phase Recognition Results -- 4.4 Offline Surgical Phase Recognition Results -- 4.5 Ablation Study -- 4.6 Qualitative Analysis -- 5 Conclusion -- References -- A Reinforced Passage Interactive Retrieval Framework Incorporating Implicit Knowledge for KB-VQA -- 1 Introduction -- 2 Related Work -- 2.1 Retrieval-Based Visual Question Answering Method -- 2.2 Large-Scale Model-Based Visual Question Answering Method -- 3 Methods -- 3.1 Implicit Knowledge-Driven Explicit Knowledge Retrieval -- 3.2 Passage Self-interaction -- 3.3 Model Training.
3.4 Retriever-Reader Generation.
Record Nr. UNINA-9910878979503321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part XI / / edited by De-Shuang Huang, Yijie Pan, Qinhu Zhang
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part XI / / edited by De-Shuang Huang, Yijie Pan, Qinhu Zhang
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (513 pages)
Disciplina 006.3
Altri autori (Persone) PanYijie
ZhangQinhu
Collana Lecture Notes in Computer Science
Soggetto topico Computational intelligence
Machine learning
Computer networks
Application software
Computational Intelligence
Machine Learning
Computer Communication Networks
Computer and Information Systems Applications
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-12-X
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part XI -- Intelligent Computing in Computer Vision -- Priority Intra-model Adaptation for Traffic Sign Detection and Recognition -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Priority Intra-model Adaptation -- 3.2 TSDR Models -- 3.3 TT100K-FineNet and GTSDB-FineNet -- 4 Experiment -- 4.1 Datasets -- 4.2 Evaluation Metrics and Implementation Details -- 4.3 Experimental Results -- 5 Discussion -- 6 Conclusion -- References -- Adaptive Swin Transformers for Few-Shot Cross-Domain Silent Face Liveness Detection -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Overview -- 3.2 Network Architecture -- 3.3 Feature-Wise Transformation -- 4 Experiment -- 4.1 Datasets and Evaluation Metrics -- 4.2 Implementation Details -- 4.3 Cross-Domain Performance -- 4.4 Ablation Study -- 5 Conclusion -- References -- DSFormer: Leveraging Transformer with Cross-Modal Attention for Temporal Consistency in Low-Light Video Enhancement -- 1 Introduction -- 2 Related Work -- 2.1 Low-Light Video Enhancement -- 3 Method -- 3.1 DSFormer Architecture -- 3.2 Flow Cross-Attention (FCA) -- 3.3 Spatial-Channel Multi-head Self-Attention (SCMA) -- 3.4 Dual Path Feed-Forward Network (DPFN) -- 4 Experiment -- 4.1 Implementation Detail -- 4.2 Static Video Evaluation -- 4.3 Dynamic Video Evaluation -- 4.4 Ablation Study -- 5 Conclusion -- References -- Robot Control Using Hand Gestures of the Mexican Sign Language -- 1 Introduction -- 2 Proposed Method -- 2.1 Segmentation Techniques -- 2.2 Feature Extraction -- 2.3 Feature Selection -- 2.4 Classification Techniques -- 2.5 Dataset -- 3 Experimental Results -- 4 Control Robot Method -- 4.1 Movement Orders Selection and Implementation -- 5 Conclusions -- References -- Improved Channel-Wise Semantic Alignment for Few-Shot Object Detection -- 1 Introduction.
2 Related Work -- 3 Problem Definition -- 3.1 Few-Shot Object Detection -- 3.2 Channel Attention -- 4 Our Method -- 4.1 Feature Purification -- 4.2 Sparse Channel Relation Distillation -- 5 Experiments -- 5.1 Datasets -- 5.2 Implementation Details -- 5.3 Comparison with the State-of-the-Arts -- 5.4 Ablation Study -- 6 Conclusion -- References -- Adapting Depth Distribution for 3D Object Detection with a Two-Stage Training Paradigm -- 1 Introduction -- 2 Related Work -- 2.1 Camera-Only 3D Object Detection -- 2.2 Depth Estimation -- 3 Preliminary -- 3.1 3D Object Detection -- 3.2 Multi-View Depth Estimation -- 3.3 LSS-Based 3D Object Detection Framework -- 4 Method -- 4.1 Two-Stage Training Paradigm -- 4.2 Depth Distribution Adaption -- 5 Experiment -- 5.1 Experimental Setup -- 5.2 Main Results -- 5.3 Ablation Study -- 5.4 Validation Test: The Impact of Depth Accuracy on Detection -- 6 Conclusion -- 6.1 Limitations -- References -- Domain Adaptive Object Detection with Dehazing Module -- 1 Introduction -- 2 Related Work -- 2.1 Image Dehazing -- 2.2 Object Detection -- 2.3 Domain Adaptive Object Detection -- 3 Methods -- 3.1 Network Overview -- 3.2 Dehazing Module -- 3.3 Domain Adaptation -- 4 Experimental Results -- 4.1 Datasets -- 4.2 Experiment of Fog Removal Module -- 4.3 Experiment of DefogDA-FasterRCNN -- 5 Conclusions -- References -- Improving Dynamic 3D Gaussian Splatting from Monocular Videos with Object Motion Information -- 1 Introduction -- 2 Related Work -- 2.1 Dynamic Scene Reconstruction -- 2.2 Depth Estimation -- 3 Preliminary -- 3.1 Problem Definition -- 3.2 3D Gaussian Splatting -- 3.3 Deformation Field -- 4 Method -- 4.1 Overview -- 4.2 Motion Segmentation -- 4.3 Three-Stage Training Strategy -- 4.4 Synthetic View Augmentation -- 5 Experiment -- 5.1 Setting -- 5.2 Comparisons -- 5.3 Ablation Study -- 6 Conclusion -- References.
Segmentation and Quality Assessment of Continuous Fitness Movements Based on Vision -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 WaveOptiSeg -- 3.2 TimeTransMLP -- 4 Experiments -- 4.1 Squat-Score Dataset -- 4.2 Evaluation Metrics -- 4.3 Implementation Details -- 4.4 Performance Comparison -- 5 Conclusion -- References -- Diagonal-Angle-Foreground IoU Loss Function for Small Object Detection -- 1 Introduction -- 2 Related Work -- 2.1 IoU Series Loss Functions for Bounding Box Regression -- 2.2 Summary -- 3 DAFIoU Loss Function -- 3.1 Angle-Based Loss Term -- 3.2 Diagonal-Based Loss Term -- 3.3 Foreground-Based Loss Term -- 3.4 DAFIoU (Diagonal, Angle, and Foreground Loss Function) -- 4 Experimental Results -- 4.1 Simulated Experiment -- 4.2 Ablation Experiment -- 4.3 YOLOv8s on Visdrone2019 -- 4.4 YOLOv8s on SODA-D10 -- 4.5 Faster R-CNN on Visdrone2019 -- 4.6 Visualization of Detection Results -- 5 Conclusion -- References -- Enhancing Dense Object Counting in Occlusion with a Dual-Branch Network -- 1 Introduction -- 2 Related Works -- 2.1 Neural Networks for Counting -- 2.2 Optimization Method of Dense Object Counting -- 3 Bilateral Counting Network -- 3.1 Density Region Extraction -- 3.2 Multi-lateral Collaborative Counting Network -- 4 Experiments -- 4.1 Datasets -- 4.2 Experiment Settings -- 4.3 Experiment Results -- 5 Analysis -- 5.1 Ablation Studies -- 6 Limitations -- 7 Conclusion -- References -- Street Block Classification Based on Urban Satellite Images -- 1 Introduction -- 2 Dataset Building and Reprocessing -- 2.1 Dataset Building -- 2.2 Preprocessing of Public Datasets -- 3 Our Network Architecture -- 3.1 Feature Extractor -- 3.2 Adaptive Pyramid Pooling -- 3.3 Classifier -- 4 Experiments -- 4.1 Overall Accuracy -- 4.2 F1 Score -- 5 Conclusion -- References.
SRCFT: A Correlation Filter Tracker with Siamese Super-Resolution Network and Sample Reliability Awareness for Thermal Infrared Target Tracking -- 1 Introduction -- 2 Methodology -- 2.1 Algorithm Overview -- 2.2 Siamese Super-Resolution Network -- 2.3 Sample Reliability Awareness -- 3 Experiment -- 3.1 Implementation Details -- 3.2 Performance Comparison with State-of-the-Arts -- 4 Conclusions -- References -- Traffic Sign Detection and Recognition Using Gradient Training with an Improved YOLO Network -- 1 Introduction -- 2 Tri-modal Gradient Based Dataset Processing -- 2.1 First Gradient Dataset -- 2.2 Second Gradient Dataset -- 2.3 Third Gradient Dataset -- 3 IYOLO-TS -- 4 Experiments and Results -- 5 Summary and Outlook -- References -- Neural Radiation Fields via Accelerated and High Quality Parallel for Novel View Synthesis -- 1 Introduction -- 2 Related Work -- 2.1 Novel View Synthesis -- 2.2 Neural Radiance Fields -- 2.3 NeRFs with Explicit Volumetric Representations -- 3 Background and Motivation -- 4 Method -- 5 Experiments -- 5.1 Experiment Setup -- 5.2 Evaluation on Quality and Efficiency -- 5.3 Training on Consumer Devices -- 5.4 Comparison of Ablation Experiments -- 6 Conclusion -- References -- IOCSegFormer: Enhancing Wheat Ears Counting in Field Conditions Through Augmented Local Features -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 The Architecture -- 3.2 Local Segmentation Branch -- 3.3 Loss Function -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Datasets -- 4.3 Data Preprocessing -- 4.4 Results and Analysis -- 4.5 Ablation Studies -- 4.6 Visualizations -- 5 Conclusion -- References -- Stroke-Based Few-Shot Chinese Character Style Transfer -- 1 Introduction -- 2 Method -- 2.1 Dataset -- 2.2 Overall Pipeline -- 2.3 Cross-attention Module -- 2.4 Loss Functions -- 3 Result and Discussions -- 3.1 Evaluation Metrics.
3.2 Generated Chinese Character Images Results -- 4 Conclusion -- References -- Computer Vision Drives the New Quality Productive Forces in Agriculture: A Method for Recognizing Farming Behavior on Edge Computing Devices -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 Employee Detection -- 3.2 Behavior Classification -- 4 Experiments and Results -- 4.1 Dataset -- 4.2 Implementation Details -- 4.3 Evaluation Metrics -- 4.4 Experimental Results -- 5 Conclusions and Future Works -- References -- PS-DeiT: A Part-Selection Based DeiT for Fine-Grained Classification -- 1 Introduction -- 2 Related Work -- 3 Part-Selection Based DeiT -- 3.1 DeiT Based Feature Extractor -- 3.2 Knowledge Distillation Model -- 3.3 Part Selection Module -- 3.4 Loss Function Design -- 4 Experimental Results and Analysis -- 4.1 Implementation Details -- 4.2 Performance Evaluation -- 4.3 Ablation Study -- 5 Conclusion -- References -- Text-Guided Multi-region Scene Image Editing Based on Diffusion Model -- 1 Introduction -- 2 Method -- 2.1 Overview -- 2.2 Mask Dilation Based Object Editing -- 2.3 OutwardLPF Based Background Coordination -- 3 Experimental Evaluation -- 3.1 Implementation Details -- 3.2 Main Results -- 3.3 Ablation Study -- 3.4 Scene Iterative Editing -- 4 Conclusion -- References -- MFANet: Multi-feature Aggregation Network for Domain Generalized Stereo Matching -- 1 Introduction -- 2 Related Work -- 2.1 Deep Stereo Matching -- 2.2 Domain Generalization -- 3 Method -- 3.1 Network Architecture -- 3.2 Multi-scale Adaptive Semantic Feature Aggregation -- 3.3 Multi-scale Texture Feature Aggregation -- 3.4 Recurrent Hourglass Aggregation Network -- 3.5 Disparity Regression and Loss Function -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Ablation Studies -- 4.3 Comparison with State-of-the-Art -- 4.4 Cross-Domain Generalization -- 5 Conclusion.
References.
Record Nr. UNINA-9910878065803321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part XIII / / edited by De-Shuang Huang, Wei Chen, Qinhu Zhang
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part XIII / / edited by De-Shuang Huang, Wei Chen, Qinhu Zhang
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (536 pages)
Disciplina 006.3
Altri autori (Persone) ChenWei
ZhangQinhu
Collana Lecture Notes in Computer Science
Soggetto topico Computational intelligence
Machine learning
Computer networks
Application software
Computational Intelligence
Machine Learning
Computer Communication Networks
Computer and Information Systems Applications
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-18-9
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part XIII -- Knowledge Discovery and Data Mining -- LeadRec: Towards Personalized Sequential Recommendation via Guided Diffusion -- 1 Introduction -- 2 Related Work -- 2.1 Sequence Recommendation -- 2.2 Diffusion Model -- 3 Preliminary -- 3.1 Forward Process -- 3.2 Reverse Process -- 3.3 Optimization -- 4 Lead Diffusion Recommender Model -- 4.1 LeadRec -- 4.2 LeadRec Blocks -- 5 Experiments -- 5.1 Dataset and Evaluation Metrics -- 5.2 Baselines and Training Protocol -- 5.3 Main Results -- 5.4 Further Analysis -- 6 Conclusion and Limitations -- References -- Anomaly Detection Method for Multivariate Time Series Data Based on BLTranAD -- 1 Introduction -- 2 Related Work -- 3 Methods -- 4 Experiment -- 4.1 Baseline -- 4.2 Dataset -- 4.3 Data Preprocessing -- 4.4 Experimental Settings -- 4.5 Evaluation Indicators -- 4.6 Results -- 5 Conclusion -- References -- MANet: A Mining and Analysis Method of Air Pollutants Transmission Path Network -- 1 Introduction -- 2 Methods -- 2.1 Related Work -- 2.2 Framework -- 2.3 Select Valid Data -- 2.4 Single Source Diffusion Influence Factor -- 2.5 Causal Mechanism-Oriented Construction Method -- 3 Experiment and Characteristic Analysis -- 3.1 The Generation of Pollutant Transmission Path Network -- 3.2 Validation and Analysis -- 4 Conclusion -- References -- HRMNN: Heterogeneous Relationship Mined Graph Neural Network -- 1 Introduction -- 2 Methodology -- 2.1 Node Features Projection -- 2.2 Relational Graph Generator -- 2.3 Object-Level Aggregation -- 2.4 Relation-Level Aggregation -- 3 Experiment -- 3.1 Datasets -- 3.2 Baseline -- 3.3 Node Classification -- 3.4 Node Clustering -- 3.5 Link Prediction -- 3.6 Ablation Study -- 4 Conclusion -- References -- Knowledge Completion Method Based on Relational Embedding with GNN -- 1 Introduction.
2 Knowledge Completion Based on GNN -- 2.1 Knowledge Graph Construction -- 2.2 Relational Embedding -- 2.3 Graph Neural Network (GNN) -- 2.4 Analysis of Classic Models -- 3 Discussion -- 3.1 Feature Learning Capability -- 3.2 Adaptability -- 3.3 Interpretability -- 3.4 Effective Processing of Graph-Structured Data -- 4 Conclusion -- References -- An Influence Blocking Maximization Algorithm Based on Community Division in Social Networks -- 1 Introduction -- 2 Problem Definition -- 3 Method -- 3.1 Community Division Based on Negative Seeds -- 3.2 Community Merging -- 3.3 The Allocation Process of the Positive Seeds -- 3.4 Finding Positive Seeds in the Community -- 4 Experiments and Result -- 4.1 Experimental Setting -- 4.2 Experimental Results -- 5 Conclusion -- References -- Research on Feature Selection Methods Based on Feature Clustering and Information Theory -- 1 Introduction -- 2 AP-MSU Feature Selection Model -- 2.1 Introduction to Related Work -- 2.2 Modeling Algorithm -- 3 Empirical Analysis -- 3.1 Analysis of the Effect of De-redundancy on the Dichotomous Dataset -- 3.2 De-redundancy Effect of Multi-categorization Dataset -- 4 Conclusions -- References -- A Redundant Relation Reduced Bidirectional Extraction Framework Based on SpanBERT for Relational Triple Extraction -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 SpanBERT-Based Encoder -- 3.2 Sentence Relation Prediction -- 3.3 Bidirectional Tagging Based Entity Extraction -- 3.4 Biaffine Based Relation Extraction -- 3.5 Training Strategy and Share-Aware Learning Mechanism -- 4 Experiment -- 4.1 Experiment Settings -- 4.2 Experiment Results -- 5 Conclusions -- References -- FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Task Definition.
3.2 ESCEval: A Dataset of Human ESC Evaluation -- 3.3 Proposed FEEL -- 4 Experiments and Results -- 4.1 Implementation of FEEL -- 4.2 Comparative Results -- 4.3 Ablation Experiment -- 5 Conclusion -- References -- BACP: Bayesian Augmented CP Factorization for Traffic Data Imputation -- 1 Introduction -- 2 Preliminaries -- 3 Proposed Model: BACP -- 3.1 Model Analysis -- 3.2 Variational Inference of BACP -- 3.3 Algorithm Analysis -- 4 Experiments -- 4.1 Settings -- 4.2 Results -- 5 Conclusions and Future Work -- References -- Improving Zero-Shot Stance Detection by Infusing Knowledge from Large Language Models -- 1 Introduction -- 2 Related Work -- 2.1 Zero-Shot Stance Detection -- 2.2 Data Augmentation Based on LLMs -- 3 Methodology -- 3.1 Problem Formulation -- 3.2 LLM Knowledge Generation -- 3.3 Topic-Iterative Data Augmentation -- 3.4 Knowledge Infusion -- 4 Experiments -- 4.1 Datasets and Metrics -- 4.2 Implementation Details -- 5 Results and Analysis -- 5.1 Comparison Results -- 5.2 Ablation Results -- 5.3 Case Study -- 6 Conclusion -- References -- Robust Cyberbullying Detection in Diverse Textual Noise -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Attention-Based Compositional Embedding -- 3.2 Capsule Network Based on k-Means Routing -- 3.3 Coherent Robustness Training -- 4 Experiments -- 4.1 Datasets -- 4.2 Experimental Setup -- 4.3 Evaluation Metrics -- 4.4 Baseline Methods -- 4.5 Main Results -- 4.6 Ablation Study -- 4.7 Hyperparameter Experiments -- 5 Conclusion -- References -- AVPS: Automatic Vertical Partitioning for Dynamic Workload -- 1 Introduction -- 2 AVPS Workflow -- 3 Query Encoding and Collection -- 4 Repartitioning System -- 4.1 Design of PPO Controller -- 4.2 Workload Selector -- 5 Experiment -- 5.1 Experiment Setup -- 5.2 Performance Analysis on Evaluation Model -- 5.3 Efficiency Analysis on PostgreSQL.
6 Conclusion -- References -- Multi-granularity Histories Merging Network for Temporal Knowledge Graph Reasoning -- 1 Introduction -- 2 Notations -- 3 Methodology -- 3.1 Local History Encoder -- 3.2 Attention-Based Decoder -- 3.3 Global History Gate -- 3.4 Parameter Learning -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experimental Results and Analysis -- 4.3 Ablation Study -- 4.4 Sensitivity Analysis of Global History Gate -- 4.5 Sensitivity Analysis of AttConvTransE -- 5 Conclusion -- References -- EntroMAGNN: An Entropy-Driven Metapath-Based Graph Neural Network for Maritime Emergency Event Prediction -- 1 Introduction -- 2 Related Work -- 2.1 Graph-Based Event Prediction -- 2.2 Knowledge-Based Event Prediction -- 3 Method -- 3.1 Definition -- 3.2 Model -- 4 Experiment -- 4.1 Implementation Detail -- 4.2 Main Results -- 4.3 Ablation Study and Analysis -- 4.4 Case Study -- 5 Conclusion -- References -- Rumor Detection with News Environment Enhanced Propagation Structure -- 1 Introduction -- 2 Methodology -- 2.1 Formalization -- 2.2 Graph Construction -- 2.3 Graph Embedding -- 2.4 Classification -- 3 Experiment -- 3.1 Datasets -- 3.2 Baselines -- 3.3 Experimental Settings -- 3.4 Performance Comparison -- 3.5 Ablation Analysis -- 3.6 Case Study -- 4 Conclusion -- References -- HEAMWalk: Heterogeneous Network Embedding Based on Attribute Combined Multi-view Random Walks -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Random Walk with Attribute View -- 3.2 Selection Strategy of Structure Views Under Different Meta-Paths -- 3.3 Learning Node Embeddings by Skip-Gram -- 4 Experiment -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Node Classification -- 4.4 Node Clustering -- 4.5 Parameter Analysis -- 5 Conclusion -- References -- Spatial-Temporal Dependency Based Multivariate Time Series Anomaly Detection for Industrial Processes.
1 Introduction -- 2 Method -- 2.1 Task Formalization -- 2.2 Preliminaries -- 2.3 Framework of MTVAE-GM -- 2.4 Data Preprocessing -- 2.5 Details of MTVAE-GM -- 2.6 Joint Optimization -- 2.7 Inference -- 3 Experiments -- 3.1 Datasets and Metrics -- 3.2 Setup -- 3.3 Performance Comparison -- 3.4 Ablation Study -- 3.5 Case Study -- 4 Conclusion -- References -- A Multi-Granularity Semantic Extraction Method for Text Classification -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Overview -- 3.2 Review of BERT -- 3.3 Multi-Granularity Semantic Extraction -- 3.4 Semantic Information Fusion -- 4 Experiments and Results -- 4.1 Experimental Settings -- 4.2 Comparison with the State-of-The-Arts -- 4.3 Ablation Study -- 5 Conclusion -- References -- Modality-Guided Collaborative Filtering for Recommendation -- 1 Introduction -- 2 Methodology -- 2.1 Preliminaries -- 2.2 Overview -- 2.3 Adaptive Graph Augmentation -- 2.4 Masked Graph Autoencoder -- 2.5 Model Optimization -- 3 Experimental Results -- 3.1 Datasets -- 3.2 Compared Baselines -- 3.3 Performance Comparison -- 3.4 Ablation Studies -- 3.5 Case Study -- 4 Conclusion -- References -- Reinforce Tokens for the Next Recommendation Generation -- 1 Introduction -- 2 Methodology -- 2.1 Preliminaries -- 2.2 Overview -- 2.3 Collaborative Signal Learning -- 2.4 Reinforced Token Generation -- 2.5 Instruction Tuning -- 3 Experimental Results -- 3.1 Datasets -- 3.2 Compared Baselines -- 3.3 Performance Comparison -- 3.4 Ablation Studies -- 3.5 Case Study -- 4 Conclusion -- References -- Structural Optimization and Sequence Interaction Enhancement for Hyper-Relational Knowledge Graphs -- 1 Introduction -- 2 Related Work -- 2.1 Hypergraph Structural Learning -- 2.2 Hyper-Relational Knowledge Graphs Completion -- 3 Methodology -- 3.1 Model Generalization.
3.2 Importance Information Sampling for Hypergraph Structures.
Record Nr. UNINA-9910878977303321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part X / / edited by De-Shuang Huang, Chuanlei Zhang, Jiayang Guo
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part X / / edited by De-Shuang Huang, Chuanlei Zhang, Jiayang Guo
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (548 pages)
Disciplina 006.3
Altri autori (Persone) ZhangChuanlei
GuoJiayang
Collana Lecture Notes in Computer Science
Soggetto topico Computational intelligence
Machine learning
Computer networks
Application software
Computational Intelligence
Machine Learning
Computer Communication Networks
Computer and Information Systems Applications
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 9789819756094
981975609X
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part X -- Information Security -- Eavesdropping Mobile Apps and Actions Through Wireless Traffic in the Open World -- 1 Introduction -- 2 Threat Model -- 3 System Design -- 3.1 System Overview -- 3.2 Traffic Preprocessing -- 3.3 Multi-level Feature Extraction -- 3.4 App and Action Recognition -- 4 Evaluation -- 4.1 Evaluation Methodology -- 4.2 Experimental Results -- 5 Conclusion -- References -- Improving WiFi CSI Fingerprinting with IQ Samples -- 1 Introduction -- 2 Threat Model and CSI Features -- 2.1 Threat Model -- 2.2 CSI Features -- 3 System Design -- 3.1 System Overview -- 3.2 CSI Measurement Transformation -- 3.3 Feature Extraction and Recognition -- 4 Experimental Evaluation -- 4.1 Evaluation Methodology -- 4.2 Experimental Results -- 5 Conclusions -- References -- RIHNet: A Robust Image Hiding Method for JPEG Compression -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Overview -- 3.2 Secret Image Hiding Module (SIH) -- 3.3 Classifier -- 3.4 Denoising Module -- 3.5 Loss Function -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Comparison with SOTA -- 4.3 Ablation Experiments -- 5 Conclusion -- References -- HybridHash: An Efficient Hash Index for Encrypted Databases -- 1 Introduction -- 2 Related Work -- 3 Design of HybridHash -- 3.1 Overall Structure -- 3.2 Operations -- 4 Performance Evaluation -- 4.1 Read Performance -- 4.2 Bucket-Splitting Cost -- 4.3 Index Size -- 5 Conclusions and Future Work -- References -- Textual Backdoor Attack via Keyword Positioning -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Threat Model -- 3.2 Overview -- 3.3 Calculation of the Importance Score -- 3.4 Trigger Selection -- 3.5 Generate Toxic Samples -- 3.6 Training-Time Poisoning -- 3.7 Test-Time Poisoning -- 4 Experimental Setup -- 4.1 Equipment -- 4.2 Datasets -- 4.3 Victim Models.
4.4 Baseline Methods -- 4.5 Evaluation Metrics -- 5 Experimental Results -- 5.1 Backdoor Attack Results and Discussion -- 5.2 The Impact of the Number of Operations -- 6 Conclusion -- References -- A Hybrid DCT/DST Based Embedding Framework for Video Steganography in H.265/HEVC -- 1 Introduction -- 2 Averting Intra-Distortion Drift and Spacing Coding -- 2.1 Averting Intra-Distortion Drift -- 2.2 Spacing Coding -- 3 The Architecture of the Hybrid Embedding Framework -- 3.1 Intra-Prediction Embedding and Extraction -- 3.2 Inter-Prediction Embedding and Extraction -- 4 Experimental Results -- 5 Security Analysis -- 6 Conclusion -- References -- Intelligent Computing in Computer Vision -- YOLO-FLC: Lightweight Traffic Sign Detection Algorithm -- 1 Introduction -- 2 Yolo-F -- 2.1 Improved C3 Module -- 2.2 Feature Pyramid Optimization -- 2.3 The Improvement of the Loss Function -- 2.4 Detection Scale Optimization -- 3 Model Compression -- 3.1 Pruning -- 3.2 Knowledge Distillation -- 4 Results of Experiments and Data Analysis -- 4.1 Dataset Processing -- 4.2 Evaluation Metrics -- 4.3 The Experimental Environment -- 4.4 The Experimental Results -- 5 Conclusion -- References -- Self-supervised Visual Anomaly Detection with Image Patch Generation and Comparison Networks -- 1 Introduction -- 2 Related Work -- 2.1 Unsupervised Anomaly Detection Based on Reconstruction -- 2.2 VIT-Based Network -- 2.3 Siamese Network -- 3 Method -- 3.1 VIT-Based Patch Generation Network -- 3.2 Siamese-Based Fine-Grained Comparison Network -- 3.3 Bi-directional Inference Strategy -- 4 Experiment -- 4.1 Datasets and Metrics -- 4.2 Implementation Details -- 4.3 Evaluation on MVTec AD Dataset -- 4.4 Evaluation on Our Own Dataset -- 4.5 Ablation Study -- 5 Conclusion -- References -- Spatial-Temporal Transformer Network for Continuous Action Recognition in Industrial Assembly.
1 Introduction -- 2 Related Work -- 2.1 Action Recognition for Assembly Operation -- 2.2 Human Object Interaction -- 2.3 Video Transformer -- 3 Method -- 3.1 STTN for Action Recognition -- 3.2 Operation Procedure Edition for Action Sequence Recognition -- 3.3 Continual Learning with Worker-in-the-Loop -- 4 Experiments -- 4.1 Action Recognition on Public Dataset -- 4.2 Action Recognition on Industrial Assembly Dataset -- 4.3 Promotion on Production Quality and Efficiency -- 5 Conclusion -- References -- EVF-YOLO: A Lightweight Network for License Plate Detection Under Severe Weather Conditions -- 1 Introduction -- 2 Related Work -- 3 Model Construction and Analysis -- 3.1 EMA -- 3.2 Feature Fusion V-GFPN -- 3.3 Lightweight Detection Head -- 3.4 Overall Model -- 4 Experimental Design and Result Analysis -- 4.1 Experimental Setup -- 4.2 Evaluation Metrics -- 4.3 Experimental Results -- 5 Conclusion -- References -- Quantum Robust Coding for Quantum Image Watermarking -- 1 Introduction -- 2 Proposed Method -- 2.1 Quantum Robust Coding (QRC) -- 2.2 Quantum Image Watermarking Using QRC -- 3 Experiments and Results -- 3.1 Evaluation of Watermarking with and Without QRC -- 3.2 Quantum Watermarking Evaluation by Comparison -- 4 Conclusion -- References -- Quantum-Enhanced Support Vector Machine for Large-Scale Multi-class Stellar Classification -- 1 Introduction -- 1.1 Types of Stars and Current Methods of Classification -- 2 Methodology -- 2.1 Classical Support Vector Machine -- 2.2 Quantum-Enhanced SVM with Quantum Feature Map -- 3 Feature Engineering for Stellar Classification -- 4 Results and Discussion -- 4.1 QSVM for Large Stellar Dataset with Two Classes -- 4.2 Quantum Simulator for Quantum Kernel with GPU Acceleration Using cuQuantum SDK -- 5 Conclusion -- References -- DDNet: Detection-Focused Dehazing Network -- 1 Introduction -- 2 Related Work.
2.1 Object Detection -- 2.2 Image Dehazing -- 2.3 Object Detection Under Hazy Weather -- 3 Proposed Method -- 3.1 Rep-Inception -- 3.2 Dual-Branch Fusion Network -- 3.3 Parallel Differentiable Image Processing Module -- 4 Experiments -- 4.1 Datasets -- 4.2 Comparison with Other Methods -- 4.3 Ablation Study -- 5 Conclusion -- References -- A Secure Voting Scheme Based on Quantum Walk -- 1 Introduction -- 2 Preliminary -- 2.1 One-Dimensional Quantum Walk Model on the Line -- 2.2 Teleportation Based on Quantum Walks -- 3 Security Voting Scheme -- 3.1 Quantum Voting System Model -- 3.2 Authorization of Legitimate Voters -- 3.3 Security Testing -- 3.4 Voting Scheme -- 4 Security Analysis -- 4.1 Non-reusability -- 4.2 Verifiability -- 4.3 Privacy and Security -- 4.4 Fairness -- 5 Comparison -- 6 Conclusion -- References -- PyCIM: A Python Framework for the Dynamics of Coherent Ising Machine -- 1 Introduction -- 2 The Principle of CIM -- 3 The Architecture of PyCIM -- 3.1 Existing Theoretical Models Describing CIM -- 3.2 Design of PyCIM -- 4 Experiments -- 4.1 The Evolution of DOPO State in CIM Without Coupling -- 4.2 The Process of CIM Solving MAX-CUT Problem -- 4.3 The Influence of Coupling Strength and Pump Scheduling on Solution Performance -- 4.4 The Performance of PyCIM on G-Set -- 5 Conclusion -- References -- Dense Center Point Mechanism: A Novel Approach for Multi-expert Decision Integration in Portfolio Management -- 1 Introduction -- 2 Methodology -- 2.1 Problem Definition -- 2.2 Expert Consensus Decision-Making Method -- 3 Integrate Expert Decision Process -- 3.1 Behavior and Definition of CPESM Experts -- 3.2 Portfolio Optimization of Investor -- 4 Empirical Approach -- 4.1 Experimental Setup -- 4.2 DEDIS Results Analysis -- 4.3 Portfolio Results Analysis -- 5 Conclusion -- References.
Planning for Earth Imaging Tasks via Grid Significance Mapping -- 1 Introduction -- 2 Gird Division and Mapping -- 2.1 Introducing H3 Gridding -- 2.2 Significance Mapping of Points -- 3 Task Planning Using Grid Representations -- 3.1 Grid-Based Planning Model -- 3.2 Planning Problem Solving -- 4 Experiments and Evaluation -- 4.1 Experiment Settings -- 4.2 Significance of Weight Mapping -- 4.3 Experimental Analysis of Load Balancing -- 5 Conclusion and Future Work -- References -- Virtual Reality and Human-Computer Interaction -- FusionCraft: Fusing Emotion and Identity in Cross-Modal 3D Facial Animation -- 1 Introduction -- 2 Related Works -- 3 Method -- 3.1 Overview -- 3.2 Preliminaries -- 3.3 Text2Avatar -- 3.4 Emotion-Identity Fusion Module -- 3.5 Avatar Generator -- 3.6 Key Points Loss -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Evaluation Methods -- 4.3 Quantitative Evaluation -- 4.4 Qualitative Evaluation -- 4.5 User Study -- 5 Limitations and Future Work -- 6 Conclusion -- References -- DWMF: A Method for Hybrid Multimodal Intent Fusion Based on Dynamic Weights -- 1 Introduction -- 2 Related Work -- 3 Materials and Methods -- 3.1 Algorithm Description -- 3.2 Analysis of Algorithm -- 4 Experiment Steps and Results -- 4.1 Experiment Setting -- 4.2 Experiment Methods -- 4.3 Experiment Results and Analysis -- 5 Conclusion -- References -- Panoramic Video Inter Frame Prediction and Viewport Prediction Based on Background Modeling -- 1 Introduction -- 2 Related Works -- 2.1 Panoramic Video Coding -- 2.2 Viewport Prediction -- 3 Methodology -- 3.1 Background Modeling -- 3.2 Background Modeling-Based Encoding -- 3.3 Viewport Prediction -- 4 Experiments -- 4.1 Background Modeling -- 4.2 Panoramic Video Encoding -- 4.3 Viewport Prediction -- 5 Conclusion -- References.
Efficient Sensing Network and Decoupled Neural Model for Hand Pose Estimation.
Record Nr. UNINA-9910878046503321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part IX / / edited by De-Shuang Huang, Wei Chen, Jiayang Guo
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part IX / / edited by De-Shuang Huang, Wei Chen, Jiayang Guo
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (511 pages)
Disciplina 006.3
Altri autori (Persone) ChenWei
GuoJiayang
Collana Lecture Notes in Computer Science
Soggetto topico Computational intelligence
Machine learning
Computer networks
Application software
Computational Intelligence
Machine Learning
Computer Communication Networks
Computer and Information Systems Applications
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-06-5
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part IX -- Information Security -- Non-targeted Adversarial Attacks on Object Detection Models -- 1 Introduction -- 2 Related Work -- 2.1 Adversarial Attacks Against Classification Models -- 2.2 Adversarial Attacks Against Object Detection Models -- 2.3 Targeted Attack and Non-targeted Attack -- 3 Generate Adversarial Examples -- 3.1 Overcoming the NMS Mechanism -- 3.2 UnTargeted Adversary -- 4 Experiment -- 4.1 Experiments Setup -- 4.2 Result on Object Detection Comparison with State-Of-The-Art Methods -- 4.3 The Denseness of Proposals -- 4.4 Perceptibility -- 5 Conclusion -- References -- Block Cipher Algorithms Identification Scheme Based on KFDA -- 1 Introduction -- 2 Related Work -- 3 Block Cipher Algorithm Identification Scheme -- 3.1 Block Cipher Algorithm Identification -- 3.2 Hamming Weight Based Ciphertext Feature Extraction Method -- 3.3 Data Mapping Based on Kernel Fisher Discriminant Analysis -- 4 Experimental Preparation -- 4.1 Data Mapping Based on Kernel Fisher Discriminant Analysis -- 4.2 Graded Result Evaluation Criteria -- 5 Evaluation and Comparison of Experimental Results -- 5.1 Experimental Results of Block Cipher with Fixed Keys -- 5.2 Experimental Results of Block Cipher with Random Keys -- 6 Conclusion -- References -- Network Traffic Intrusion Detection Strategy Based on E-GraphSAGE and LSTM -- 1 Introduction -- 2 Problem Description and Methodology -- 2.1 Problem Description -- 2.2 Framework -- 2.3 Data Processing -- 2.4 Traffic Graph Construction -- 2.5 E-GraphSAGE Layer -- 2.6 LSTM Layer -- 3 Experiments and Results Analysis -- 3.1 Dataset -- 3.2 Experimental Setup -- 3.3 Experimental Metrics -- 3.4 Analysis of Results -- 3.5 Ablation Experiments -- 4 Conclusion -- References -- A State of the Art Review on Artificial Intelligence-Enabled Cyber Security in Smart Grid.
1 Introduction -- 2 Related Works -- 2.1 Security Threats -- 2.2 Artificial Intelligence and Machine Learning -- 3 Network Security in Smart Grid -- 3.1 Security Countermeasures -- 3.2 Analyzing and Comparing -- 4 AI-Based Cyber Security -- 5 Conclusion -- References -- Reversible Data Hiding Based on Octree Partitioning and Arithmetic Coding in Encrypted Three-Dimensional Mesh Models -- 1 Introduction -- 2 Proposed Method -- 2.1 Pre-processing -- 2.2 Octree-Based Spatial Subdivision and Prediction Error Detection -- 2.3 Encryption -- 2.4 Data Embedding -- 2.5 Data Extraction and Mesh Recovery -- 3 Experimental Results and Analysis -- 3.1 Embedding Capacity Analysis -- 3.2 Performance Comparison -- 3.3 Model Restoration Quality Evaluation -- 4 Conclusion -- References -- A Differential Privacy Federated Learning Scheme with Improved Noise Perturbation -- 1 Introduction -- 2 Related Work -- 2.1 Federated Learning -- 2.2 Differential Privacy -- 3 Our Approach -- 3.1 Adjust Gradient Norm Clip Bound -- 3.2 Improved Noise Reduction -- 3.3 Privacy Cost Analysis -- 3.4 Improved Differential Privacy Federated Learning Algorithm -- 4 Experiment -- 4.1 Experiment Details -- 4.2 Private Cost -- 4.3 Accuracy -- 5 Conclusion -- References -- U-shaped Vertical Split Learning with Local Differential Privacy for Privacy Preserving -- 1 Introduction -- 2 System Design -- 2.1 Threat Model -- 2.2 System Model -- 3 Experiment -- 3.1 Experimental Settings -- 3.2 Experimental Results and Evaluation -- 4 Conclusion -- References -- An Intrusion Detection Method for Industrial Internet Fusing Multi-Scale TCN and Transformer Network -- 1 Introduction -- 2 Methodology -- 2.1 Overview of the Proposed Model -- 2.2 Improved Multi-scale Temporal Convolutional Network -- 2.3 Multiscale Patch Integrated Transformer -- 2.4 Parallel Branch Fusion -- 3 Results and Analysis.
3.1 Dataset Description -- 3.2 Evaluation Metrics -- 3.3 Implementation Details -- 3.4 Performance Comparison -- 3.5 Ablation Study -- 4 Conclusion -- References -- CSQF-BA: Efficient Container Query Technology for Cloud Security Query Framework with Bat Algorithm -- 1 Introduction -- 2 Related Work -- 2.1 Docker Applications and Docker Volume -- 2.2 Definition -- 3 Cloud Computing Security Query -- 4 Query Architecture with Docker Volume -- 5 Finding Algorithm in Volume -- 5.1 ACFA-BA, SFA-BA, and RFA-BA -- 5.2 Cloud Security Query Framework with Bat Algorithm (CSQF-BA) -- 6 Experiment -- 7 Conclusion -- References -- Full Database Reconstruction: Leakage-Abuse Attacks Based on Expected Distributions -- 1 Introduction -- 2 Model -- 2.1 Adversary Model -- 2.2 Reconstruction Attack -- 2.3 Edge Domain -- 3 Attack -- 3.1 Full Ordering Reconstruction -- 3.2 Full Database Reconstruction -- 3.3 Adaptive Attack -- 4 Experiment -- 4.1 Full Ordering Reconstruction -- 4.2 Full Database Reconstruction -- 4.3 Adaptive Attack -- 5 Conclusion and Future Work -- References -- FedURL: A BERT-based Federated Malicious URL Detection Framework -- 1 Introduction -- 2 Methodology -- 2.1 Federated Learning -- 2.2 Parameter-Efficient Fine-Tuning -- 2.3 FedURL -- 3 Experiment -- 3.1 Dataset -- 3.2 Implementation and Setup -- 3.3 Model Performance -- 3.4 Performance and Network Traffic of Federated Learning with Different Training Parts -- 3.5 Performance Comparison with Varied Client Numbers -- 3.6 Analysis of Client Number Impact on Training strategy in Federated Learning -- 3.7 Performance Evaluation using Real-world Dataset -- 4 Results and Discussion -- References -- Show Criminals' True Color: Chinese Variant Toxic Text Restoration Based on Pointer-Generator Network -- 1 Introduction -- 2 Related Work -- 2.1 Variant Toxic Text Detection and Restoration.
2.2 Pointer Mechanism -- 3 Methodology -- 3.1 Sequence-To-Sequence Model -- 3.2 Pointer-Generator Networks -- 4 Experiments Settings -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Evaluation Metric -- 5 Experiment Results and Analysis -- 5.1 Data Analysis and Variant Rules Extraction -- 5.2 Evaluation of Model Performance -- 5.3 Case Study -- 6 Conclusion -- References -- Adversarial Attacks on Network Intrusion Detection Systems Based on Federated Learning -- 1 Introduction -- 2 Adversarial Attack Scheme -- 2.1 Overview -- 2.2 Adversarial Sample Generation Method -- 2.3 Poisoning Attack Method -- 3 Experiment -- 3.1 Datasets and Evaluation Metrics -- 3.2 Experiment Results and Analysis -- 4 Conclusion -- References -- An EWMA-Based Mitigation Scheme Against Interest Flooding Attacks in Named Data Networks -- 1 Introduction -- 2 System Model -- 3 The Proposed EBMS -- 4 Performance Evaluation -- 4.1 Impacts of IFAs and bIFA on Network -- 4.2 Effectiveness of Attack Mitigation -- 5 Conclusions -- References. -- CAKGC: A Clustering Method of Cybercrime Assets Knowledge Graph Based on Feature Fusion -- 1 Introduction -- 2 Related Work -- 2.1 Detection Methods for Cybercrime Websites -- 2.2 Operation Chain of Cybercrime Underground Industry -- 2.3 Knowledge Graph Embedding -- 3 Methodology -- 3.1 Construction of Cybercrime Assets Knowledge Graph -- 3.2 Clustering of Cybercrime Assets Knowledge Graph -- 4 Experiment -- 4.1 Dataset -- 4.2 Evaluation Metrics -- 4.3 Comparison Algorithms -- 4.4 Experimental Results -- 5 Conclusion -- References -- Multi-texture Fusion Attack: A Robust Adversarial Camouflage in Physical World -- 1 Introduction -- 2 Related Work -- 2.1 Physical Camouflage Attack -- 3 Method -- 3.1 The Definition of Problem -- 3.2 Framework Overview -- 3.3 Generate Adversarial Camouflage -- 3.4 Expectation Over Transformation.
3.5 Physical Transformation -- 4 Experiment -- 4.1 Experimental Setting -- 4.2 Adversarial Attack in the Digital Space -- 4.3 Adversarial Attack in the Physical Space -- 4.4 Ablation Studies -- 5 Conclusion -- References -- When Blockchain Meets Asynchronous Federated Learning -- 1 Introduction -- 2 Categorization Based on Blockchain Extensions -- 2.1 Blockchain Based on Directed Acyclic Graph -- 2.2 Traditional Blockchain -- 3 Categorization Based on Coupling Approaches -- 3.1 Fully Coupled BCFL -- 3.2 Flexibly Coupled BCFL -- 3.3 Loosely Coupled BCFL -- 4 Challenges and Future Directions -- 5 Conclusion -- References -- A High-Dimensional Data Trust Publishing Method Based on Attention Mechanism and Differential Privacy -- 1 Introduction -- 2 Preliminaries -- 2.1 Differential Privacy -- 2.2 Attention Mechanism -- 3 AMPriv Method -- 3.1 ACHD -- 3.2 NAS -- 3.3 NMEGreedybayes -- 3.4 NMENoisyConditionals -- 3.5 Sampling -- 4 Experiments -- 4.1 Experimental Environment and Setup -- 4.2 Method Performance Analysis -- 4.3 Data Availability Analysis -- 5 Conclusion -- References -- PTGroup: An Automated Penetration Testing Framework Using LLMs and Multiple Prompt Chains -- 1 Introduction -- 2 Related Work -- 2.1 Penetration Testing -- 2.2 Autonomous Agents -- 3 Methodology -- 3.1 Thought-Act-Observe Loop -- 3.2 Multi-agent Framework -- 3.3 Multiple Prompt Chains -- 4 Experiments -- 4.1 Experimental Environment -- 4.2 Results and Discussion -- 5 Conclusion -- References -- Spammer Group Detection Approach Based on Deep Reinforcement Learning -- 1 Introduction -- 2 Related Work -- 2.1 Group Behavior-Based Approaches -- 2.2 Graph-Based Approaches -- 3 The Proposed Detection Method DRL-AE -- 3.1 Obtaining the Initial User Node Embeddings -- 3.2 Generating the Candidate Groups -- 3.3 Detecting Spammer Groups -- 4 Experiments -- 4.1 Experiments Datasets.
4.2 Evaluation Metrics.
Record Nr. UNINA-9910878050303321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part VIII / / edited by De-Shuang Huang, Wei Chen, Yijie Pan
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part VIII / / edited by De-Shuang Huang, Wei Chen, Yijie Pan
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (525 pages)
Disciplina 006.3
Altri autori (Persone) ChenWei
PanYijie
Collana Lecture Notes in Computer Science
Soggetto topico Computational intelligence
Machine learning
Computer networks
Application software
Computational Intelligence
Machine Learning
Computer Communication Networks
Computer and Information Systems Applications
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-03-0
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part VIII -- Image Processing -- Protecting Image Copyrights Based on the AUL Algorithm and Blockchain -- 1 Introduction -- 2 Related Work -- 3 System Model -- 3.1 Overall Architecture -- 3.2 Deep Learning Model -- 4 Experiment About Deep Learning Model -- 4.1 Experiment Environment and Setup -- 4.2 Stability Comparison with Several Algorithms -- 4.3 Threshold Determination and Algorithm Comparison -- 4.4 Comparison with Other Deep Learning Models -- 4.5 Contract Testing -- 5 Conclusion -- References -- MAPNet: A Multi-scale Attention Pooling Network for Ultrasound Medical Image Segmentation -- 1 Introduction -- 2 Related Work -- 2.1 Medical Image Segmentation Based on U-Net and Attention Mechanism -- 2.2 Dilated Convolution -- 3 Methodology -- 3.1 MAPNet for Image Segmentation -- 3.2 Improved Encoder and Decoder -- 3.3 Attention Module for Connection -- 4 Experiments -- 4.1 Datasets, Implementation Details, and Evaluation Indicators -- 4.2 Comparison with Existing Methods -- 4.3 Ablation Study -- 5 Conclusion -- References -- Fusion of Saliency and Edge Map for Multi-operator Image Retargeting Algorithm -- 1 Introduction -- 2 Related Work -- 3 Proposed Methodology -- 3.1 Saliency Detection Based on U2Net -- 3.2 Edge Detection Based on Adaptive Canny Operator -- 3.3 Importance Map -- 3.4 Weight Calculation of Three Feature Map -- 3.5 Multi-operators -- 4 Experimental Analysis -- 4.1 Qualitative Analysis -- 4.2 Quantitative Analysis -- 4.3 Explanation of the Situation -- 4.4 Ablation Studies -- 5 Conclusion -- References -- MOD-YOLO: Improved YOLOv5 Based on Multi-softmax and Omni-Dimensional Dynamic Convolution for Multi-label Bridge Defect Detection -- 1 Introduction -- 2 Related Works -- 2.1 Object Detection Networks -- 2.2 Defect Detection Methods -- 2.3 Defect Detection Methods.
3 Proposed Method -- 3.1 Defect Detection Methods -- 3.2 Multi-softmax for Detection -- 3.3 Enhancements in Backbone Network with ODConv -- 4 Result Analysis -- 4.1 Experimental Environment and Dataset -- 4.2 Comparison Experiments -- 4.3 Ablation Experiments -- 5 Conclusion -- References -- Color Image Steganography Based on Two-Channel Preprocessing and U-Net Network -- 1 Introduction -- 2 Related Works -- 2.1 U-Net Structure -- 2.2 SENet Attention Mechanism -- 3 Proposed Method -- 3.1 Preprocessing Network -- 3.2 Hiding Network -- 3.3 Extracting Network -- 3.4 Loss Function -- 4 Experimental Results -- 4.1 Visual Effects -- 4.2 Image Quality -- 4.3 Ablation Experiment -- 4.4 Steganography Capacity -- 4.5 Robustness Analysis -- 5 Conclusions -- References -- Application of a Hybrid Particle Image Velocimetry Method Based on Window Function in the Field of Turbulence -- 1 Introduction -- 2 Related Work -- 2.1 Turbulent Particle Images -- 2.2 Test Evaluation Criteria -- 3 The Specific Application Process of Window Function in Particle Image Velocimetry -- 4 Experimental Design and Simulation -- 5 Conclusion -- References -- Semantics-Enhanced Refiner in Skip Connection for Crack Segmentation -- 1 Introduction -- 2 Methodology -- 2.1 Feature Extraction Block -- 2.2 Semantics-Enhanced Refiner (SER) -- 2.3 Loss Function -- 3 Experiential Results and Analysis -- 3.1 Datasets -- 3.2 Evaluation Metrics -- 3.3 Experimental Settings -- 3.4 Result Analysis -- 3.5 Ablation Experiment -- 4 Conclusion -- References -- Refinement Correction Network for Scene Text Detection -- 1 Introduction -- 2 Related Work -- 2.1 Transformer Based Methods -- 2.2 CNN Based Regression Methods -- 2.3 CNN Based Segmentation Methods -- 3 Propose Method -- 3.1 Overall Framework -- 3.2 Rough Feature Refinement Module -- 3.3 Clue Feature Correction Module -- 4 Experiment.
4.1 Datasets -- 4.2 Experimental Setup -- 4.3 Ablation Experiment -- 4.4 Comparative Experiment -- 5 Conclusion -- References -- Weight Uncertainty Network for Low-Light Image Enhancement -- 1 Introduction -- 2 Related Work -- 2.1 Low-Light Image Enhancement -- 2.2 Bayesian Neural Network -- 3 Method -- 3.1 Weight Uncertainty in Neural Networks -- 3.2 Architecture Formulation and Non-Reference Losses -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Comparison with State-of-the-Arts -- 4.3 Ablation Study -- 5 Conclusion -- References -- Unsupervised Extremely Low-Light Image Enhancement with a Laplacian Pyramid Network -- 1 Introduction -- 2 Related Work -- 3 Unsupervised Extremely Low-Light Image Enhancement with a Laplacian Pyramid Network -- 3.1 Motivations -- 3.2 Networks -- 3.3 Loss Functions -- 4 Experimental Results -- 4.1 Datasets and Training Details -- 4.2 Baselines and Evaluation Metrics -- 4.3 Comparing to State-of-the-Arts -- 4.4 Ablation Study -- 5 Conclusion -- References -- A Multimodal Fake News Detection Model with Self-supervised Unimodal Label Generation -- 1 Introduction -- 2 Related Work -- 2.1 Unimodal Fake News Detection -- 2.2 Multimodal Fake News Detection -- 3 Proposed Method -- 3.1 Feature Extraction Module -- 3.2 Multimodal Feature Fusion -- 3.3 Unimodal Label Generation -- 3.4 Model Optimization and Prediction -- 4 Experimental Analysis -- 4.1 Experimental Configurations -- 4.2 Overall Performance -- 4.3 Ablation Study -- 5 Conclusion -- References -- Image Denoising Based on an Improved Wavelet Threshold and Total Variation Model -- 1 Introduction -- 2 Preliminaries -- 2.1 Analysis of Lung CT Image Features -- 2.2 TV Framework -- 2.3 Wavelet Threshold Denoising -- 3 Methodology -- 3.1 Improved Thresholding Function -- 3.2 Proposed Method -- 4 Experimental Results and Analysis -- 5 Conclusion -- References.
A Two-Stage Coupled Learning Network for Image Deblurring -- 1 Introduction -- 2 Proposed Method -- 2.1 Network Architecture -- 2.2 Blur Feature Decoupling Stage -- 2.3 Coupled Learning Stage -- 2.4 Loss Function -- 3 Experimental Results -- 3.1 Experimental Setting -- 3.2 Comparisons with the State of the Arts -- 4 Conclusion -- References -- Palmprint Recognition Using SC-LNMF Model in Gabor Domain -- 1 Introduction -- 2 The Modified 2D Gabor Wavelet -- 2.1 The Mathematics Form of 2D Gabor Wavelet -- 2.2 Image's Gabor Representation -- 3 The Modified SC-LNMF Algorithm -- 3.1 The LNMF Algorithm -- 3.2 The SC-LNMF Algorithm -- 4 Experimental Results and Analysis -- 4.1 Test Data Preprocessing -- 4.2 Learning Feature Bases -- 4.3 Representation of Test Images -- 4.4 Recognition Results of Palmprint Images -- 5 Conclusions -- References -- SkinDiff: A Novel Data Synthesis Method Based on Latent Diffusion Model for Skin Lesion Segmentation -- 1 Introduction -- 2 Related Works -- 2.1 Skin Lesion Segmentation -- 2.2 Diffusion Model -- 3 Methods -- 3.1 Generating Foreground Stage -- 3.2 Outpainting Background Stage -- 4 Experiments -- 4.1 Dataset -- 4.2 Evaluation Metrics -- 4.3 Implementation Details -- 4.4 Evaluations and Analyses -- 5 Conclusion -- References -- MFAAnet: New Feature Extraction Network in Image Super-Resolution -- 1 Introduction -- 2 Methodology -- 2.1 The Overall Structure -- 2.2 Multi-scale Attention Block -- 2.3 Multi-features Extraction Block -- 3 Experiments -- 3.1 Datasets and Metrics -- 3.2 Training Details -- 3.3 Ablation Study -- 3.4 Comparisons with State-of-the-Arts -- 4 Conclusion -- References -- Context-Aware Relative Distinctive Feature Learning for Person Re-identification -- 1 Introduction -- 1.1 Challenge 1: How to Leverage the Relative Nature of Distinctive Features in the Context of ReID.
1.2 Challenge 2: How to Alliviate the Confilicts Between the ID Consistency (Triplet Loss) and Visual Consistency -- 2 Method -- 2.1 Model Overview -- 2.2 Exploring Relative Discriminative Regions with Contextual Awareness -- 2.3 Visual Consistency N-Tuple Loss Function -- 3 Experiment -- 3.1 Experimental Overview -- 3.2 Performance Evaluation and Comparison -- 3.3 Performance Evaluation in Generalized Person Re-identification -- 3.4 Ablation Study -- 4 Conclusion -- References -- Image Captioning with Masked Diffusion Model -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Features Fusion -- 3.2 Masked Diffusion -- 3.3 Embedding and Rounding -- 4 Experiments -- 4.1 Experimental Setup and Implementation Details -- 4.2 Experimental Results -- 4.3 Ablation on the Key Designs -- 4.4 Hyperparameter Analysis -- 4.5 Qualitative Results -- 5 Conclusion -- References -- Textile Defect Detection Based on Multi-proportion Spatial Pyramid Convolution and Adaptive Multi-scale Feature Fusion -- 1 Introduction -- 2 Baseline Model YOLOv8 -- 3 The Proposed Model -- 3.1 Feature Extraction Stage -- 3.2 Stage of Feature Fusion -- 4 Experiment and Result -- 4.1 Experimental Environment -- 4.2 Ablation Experiments -- 4.3 Comparative Experiment -- 5 Conclusion -- References -- Real-Time Detection of Multi-scale Traffic Signs Based on Decoupled Heads -- 1 Introduction -- 2 Related Work -- 2.1 Traffic-Signs Recognition -- 2.2 Small Object Detection -- 3 Methodology -- 3.1 Additional Detection Head -- 3.2 Decoupled Head -- 3.3 Triplet Attention -- 3.4 C3RFE -- 4 Experiments and Results -- 4.1 Datasets -- 4.2 Experimental Environment -- 4.3 Experiment Results -- 4.4 Ablation Study -- 5 Conclusion -- References -- LAROD-HD: Low-Cost Adaptive Real-Time Object Detection for High-Resolution Video Surveillance -- 1 Introduction -- 2 Related Works -- 2.1 Small Object Detection.
2.2 Object Detection on High-Resolution Images.
Record Nr. UNINA-9910878982303321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part I / / edited by De-Shuang Huang, Xiankun Zhang, Qinhu Zhang
Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part I / / edited by De-Shuang Huang, Xiankun Zhang, Qinhu Zhang
Autore Huang De-Shuang
Edizione [1st ed. 2024.]
Pubbl/distr/stampa Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Descrizione fisica 1 online resource (521 pages)
Disciplina 006.3
Altri autori (Persone) ZhangXiankun
ZhangQinhu
Collana Lecture Notes in Artificial Intelligence
Soggetto topico Artificial intelligence
Computers
Computer networks
Data mining
Image processing - Digital techniques
Computer vision
Software engineering
Artificial Intelligence
Computing Milieux
Computer Communication Networks
Data Mining and Knowledge Discovery
Computer Imaging, Vision, Pattern Recognition and Graphics
Software Engineering
Intel·ligència computacional
Xarxes d'ordinadors
Aprenentatge automàtic
Programari d'aplicació
Soggetto genere / forma Congressos
Llibres electrònics
ISBN 981-9756-63-4
Formato Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione eng
Nota di contenuto Intro -- Preface -- Organization -- Contents - Part I -- Machine Learning -- A Dynamic Collaborative Recommendation Method Based on Multimodal Fusion -- 1 Introduction -- 2 Related Works -- 2.1 Multi-modal Recommendation -- 2.2 Transformer for Recommendation -- 3 Methodology -- 3.1 Data Preprocessing and Feature Extraction -- 3.2 Bi-towernet -- 3.3 Deep Canonical Correlation Analysis -- 3.4 Short Term Recommendation Based on Dynamic Time Windows -- 3.5 Optimization -- 4 Experiments -- 4.1 Datasets -- 4.2 Metrics -- 4.3 Details -- 4.4 Results -- 5 Conclusion -- References -- Image Classification Using Graph Regularized Independent Constraint Low-Rank Representation -- 1 Introduction -- 2 Related Work -- 2.1 Low-Rank Representation -- 2.2 Manifold Learning for Graph Regularization -- 3 Proposed Method -- 3.1 Hilbert-Schmidt Independence Criterion -- 3.2 Model of GRI-LRR and Its Optimization Procedure -- 4 Experiments -- 4.1 Data Sets -- 4.2 Sensitivity Analysis of GRI-LRR -- 4.3 Experiment Results and Analysis -- 4.4 Ablation Analysis -- 5 Conclusion and Future Work -- References -- Identifying the Fraudulent Users for E-commerce Applications Based on the Access Behaviors -- 1 Introduction -- 2 Methodology -- 2.1 Behavior Feature Extraction -- 2.2 Feature Encoding and Compression -- 2.3 Spatial Relations and Identification -- 3 Experiments -- 3.1 Datasets -- 3.2 Hyperparameter Sensitivity Testing -- 3.3 Component Necessity Testing -- 3.4 Comparison with Baselines -- 3.5 Stability Assessment -- 4 Conclusion -- References -- LIFT: Discriminant Classification Approach of Malware Family on Time Consistent Open Set -- 1 Introduction -- 2 Related Work -- 2.1 Malware Open Set Recognition (MOSR) -- 2.2 Malware Recognition with Temporal Bias -- 3 Methodology -- 3.1 Overview -- 3.2 Feature Extraction Based on Linear Probe Boosted Swin Transformer.
3.3 Feature Truncation Based on Distance -- 4 Experiment -- 4.1 Dataset -- 4.2 Evaluation Metrics -- 4.3 Experimental Settings -- 4.4 Baselines -- 4.5 Experimental Results -- 5 Conclusion -- References -- Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL -- 1 Introduction -- 2 Related Work -- 2.1 Few-Shot Semantic Role Labeling -- 2.2 Structured Information in Language Models -- 2.3 Prompt-Based Learning -- 3 PromptSRL -- 3.1 Stage I: Predicate Disambiguation -- 3.2 Stage II: Role Retrieval -- 3.3 Stage III: Argument Labeling -- 3.4 Stage IV: Post-process -- 4 Experiment -- 4.1 Dataset -- 4.2 Setup -- 5 Results -- 5.1 LLMs' Potential -- 5.2 LLMs' Limitations -- 5.3 Impact of Exemplars -- 5.4 Comparison with Untrained Humans -- 5.5 Ablation Study -- 6 Conclusion -- References -- Cache Side-Channel Attacks Detection for AES Encryption Based on Machine Learning -- 1 Introduction -- 2 Background and Related Work -- 2.1 Cache Side-Channel Attack -- 2.2 Hardware Performance Counters -- 2.3 Related Work -- 3 Experiment Preparation -- 4 Finding the Critical Sampling Interval -- 5 Build Attack Detection -- 6 Conclusion and Discussion -- References -- WARM: An Interpretability Module with Weighted Association Rule Mining for Recommendation Systems -- 1 Introduction -- 2 Proposed Method -- 2.1 Theory -- 2.2 Weight Settings -- 2.3 Weighted Association Rule Mining: WARM -- 2.4 An Interpretability Module with WARM for Recommendation Systems -- 3 Experiments -- 3.1 Experimental Settings -- 3.2 Evaluation of Interpretability (RQ1) -- 3.3 Detailed Study (RQ2) -- 3.4 Case Study (RQ3) -- 4 Conclusions -- References -- Globally Convergent Accelerated Algorithms for Multilinear Sparse Logistic Regression with 0-Constraints -- 1 Introduction -- 2 Methodology -- 2.1 Problem Statement -- 2.2 The Proposed APALM+ Algorithm.
3 Convergence Analysis -- 3.1 Monotonic Convergence -- 3.2 Global Convergence -- 4 Numerical Experiments -- 4.1 Baseline Methods -- 4.2 Experiments on Synthetic Data -- 4.3 Experiments on Real Data -- 5 Conclusion -- References -- Collaborative Filtering Algorithm Based on Contrastive Learning and Filtering Components -- 1 Introduction -- 2 Social Recommendation Prediction Method Based on Filtering Components and Contrastive Learning (FMPRec) -- 2.1 Problem Definition -- 2.2 Model Framework -- 2.3 Model Optimization -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Evaluation Metrics -- 3.3 Overall Performance Analysis -- 3.4 Sensitivity Analysis -- 3.5 Analysis of Factors Influencing -- 4 Conclusion -- References -- IBAS-SVM Rolling Bearing Fault Diagnosis Method Based on Empirical Modal Characteristics -- 1 Introduction -- 2 EEMD-FE-IBAS-SVM Model -- 3 Combined Feature Extraction -- 4 IBAS-SVM Fault Diagnosis Model -- 4.1 Information Sharing Characteristic -- 4.2 Adaptive Step Size -- 5 Experiments and Analysis of Results -- 5.1 Experiments on CWRU Datasets -- 5.2 Experiments on IMS Datasets -- 6 Conclusion -- References -- Using Graph Neural Network to Analyse and Detect Annotation Misuse in Java Code -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Annotation Usage Project Structure Graph(AUPSG) Generation -- 3.2 Structure-Aware GNN Based Model -- 3.3 Intergrated into IDE -- 4 Experiment -- 4.1 Dataset -- 4.2 Evaluation Metrics -- 4.3 Baselines -- 4.4 Effectiveness Evaluation in Test Dataset(RQ1) -- 4.5 Effectiveness Evaluation in Real World Project(RQ2) -- 4.6 Case Study -- 5 Conclusion -- References -- Graph Causal Contrastive for Partial Label Learning -- 1 Introduction -- 2 Related Work -- 2.1 Partial Label Learning -- 2.2 Causal Learning -- 3 Preliminaries -- 4 Method -- 4.1 Causal View of Data-Generating Process.
4.2 Causal and Non-causal Subgraph Segmentation -- 4.3 Causal Contrastive Learning -- 4.4 Causal Prototype Disambiguation -- 5 Experiments -- 5.1 Performance Evaluation -- 5.2 Feature Visualization -- 5.3 Causal and Non-causal Subgraph Analysis -- 6 Conclusions and Future Work -- References -- A Stacking Ensemble Deep Learning Model for Stock Price Forecasting -- 1 Introduction -- 2 Related Work -- 2.1 Stock Price Forecast -- 2.2 Ensemble Deep Learning -- 3 Methodology -- 3.1 Problem Formulation -- 3.2 Framework Overview -- 3.3 Gating Mechanism -- 3.4 First Base Learner -- 3.5 Second Base Learner -- 3.6 Meta Learner -- 4 Experiments -- 4.1 Datasets -- 4.2 Baselines -- 4.3 Evaluation -- 4.4 Implementation -- 4.5 Overall Comparison -- 4.6 Ablation Study -- 5 Conclusion -- References -- Smart Trading: A Novel Reinforcement Learning Framework for Quantitative Trading in Noisy Markets -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 The Overview of the Proposed Framework -- 3.2 The Customized Trading Environment -- 3.3 The Design of Trading Net with Discrete Features -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 The Adaptive Scaler in Customized Environment -- 4.3 The Comparison of Trading Performance -- 4.4 Daily Paper Trading in Live Market -- 4.5 The Importance of Using Discrete Features -- 5 Conclusion -- References -- Enhancing Image Captioning with Transformer-Based Two-Pass Decoding Framework -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Overall Framework -- 3.2 Visual Encoder -- 3.3 Draft Decoder -- 3.4 Cross-Modality Fusion Module -- 3.5 Deliberation Decoder -- 3.6 Optimization Strategy -- 4 Experimental Setup -- 4.1 Datasets and Evaluation Metrics -- 4.2 Draft Models -- 4.3 Implementation Details -- 5 Experimental Results -- 5.1 Comparing with Single-Pass Decoding Baselines.
5.2 Comparing with State-of-the-Art Methods -- 5.3 Ablation Study -- 5.4 Qualitative Analysis -- 6 Conclusion and Future Work -- References -- Ontology-Aware Overlapping Event Extraction -- 1 Introduction -- 2 Related Work -- 3 Framework -- 3.1 Ontology-Aware Semantic Encoder -- 3.2 Type Detection Decoder -- 3.3 Trigger Extractor -- 3.4 Argument Extractor -- 4 Experiments -- 4.1 Datasets and Evaluation Metrics -- 4.2 Comparison Models -- 4.3 Implementation Details -- 4.4 Experimental Analysis -- 5 Conclusion -- References -- TVD-BERT: A Domain-Adaptation Pre-trained Model for Textural Vulnerability Descriptions -- 1 Introduction -- 2 Methodology -- 2.1 Pre-training Dataset -- 2.2 Vocabulary Expansion -- 2.3 Adaptation Pre-training in TVD -- 3 Evaluation -- 3.1 Domain Similarity Analysis -- 3.2 Evaluation of Internal Task -- 3.3 Evaluation of Downstream Tasks -- 4 Enhanced Representation in DAPT -- 4.1 Limitations of MLM Tasks -- 4.2 Double Lexicon Masking -- 4.3 Evaluation of the Method -- 5 Conclusion -- References -- Improving Large Language Models in Multi-party Conversations Through Role-Playing -- 1 Introduction -- 2 The Role-Playing Multi-party Conversation Framework -- 2.1 Phase 1: Turn-Taking Phase -- 2.2 Phase 2: Utterance Phase -- 3 Experiments -- 3.1 Turn-Taking Experiment -- 3.2 Utterance Generation Experiment -- 3.3 MPC Generation Experiment -- 4 Conclusion -- Appendix -- A Prompts Used in RPMPC and the Diversity Evaluation -- References -- Context Compression and Extraction: Efficiency Inference of Large Language Models -- 1 Introduction -- 2 Optimization Algorithm -- 2.1 Computing Self-information -- 2.2 Computing Mutual-Information -- 2.3 Combining SI and MI -- 3 Experiment -- 3.1 Experimental Setup -- 3.2 Performance Correlation with Compression Ratio -- 3.3 CCE Performance on Different Tasks -- 3.4 Parameters Tuning.
3.5 Discussion.
Record Nr. UNINA-9910878987403321
Huang De-Shuang  
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
Materiale a stampa
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui