Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part VII / / edited by De-Shuang Huang, Chuanlei Zhang, Qinhu Zhang

• Pubblicazione: Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
• Edizione: 1st ed. 2024.
• Descrizione fisica: 1 online resource (492 pages)
• Disciplina: 006.3
• Soggetto topico: Computational intelligence; Computer networks; Machine learning; Application software; Computational Intelligence; Computer Communication Networks; Machine Learning; Computer and Information Systems Applications
• Persona (resp. second.): ZhangChuanlei; ZhangQinhu; HuangDe-Shuang
• Note generali: Includes index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part VII -- Image Processing -- Light-Dark: A Novel Lightweight Self-supervised Monocular Depth Estimation in the Dark -- 1 Introduction -- 2 Method -- 2.1 Nighttime Self-supervised Depth Estimation Architecture -- 2.2 Lightweight DepthNet -- 2.3 Noise-Constrained Adaptive Image Enhancement -- 2.4 Loss Function -- 3 Experiments -- 3.1 Datasets -- 3.2 Implementation Detail -- 3.3 Evaluation Results -- 3.4 Ablation Study -- 4 Conclusions -- References -- Non-homogeneous Image Dehazing with Edge Attention Based on Relative Haze Density -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 3.1 Dual-Cycle Framework Based on Relative Haze Density -- 3.2 Multi-class Discriminator -- 3.3 Loss Function -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Evaluation of Supervised Learning -- 4.3 Ablation Study -- 4.4 Evaluation of Unsupervised Learning -- 5 Conclusion -- References -- Contrastive Learning for Silent Face Liveness Detection Based on A Hybrid Framework -- 1 Introduction -- 2 Related Work -- 2.1 RGB Image-Based FLD -- 2.2 Transformers and FLD -- 3 Method -- 3.1 Overview -- 3.2 Network Architecture -- 4 Experiment -- 4.1 Datasets and Evaluation Metrics -- 4.2 Implementation Details -- 4.3 Domain Generalized Evaluation -- 4.4 Ablation Study -- 5 Conclusion -- References -- BS2CL: Balanced Self-supervised Contrastive Learning for Thyroid Cytology Whole Slide Image Multi-classification -- 1 Introduction -- 2 Related Work -- 2.1 Self-Supervised Contrastive Learning in MIL -- 2.2 Thyroid Cytology WSI Classification -- 3 Method -- 3.1 Preliminary: Problem Description -- 3.2 Balanced Self-Supervised Contrastive Learning -- 3.3 Bag-Level Data Augmentation Strategy -- 4 Experiments -- 4.1 Thyroid Cytology Dataset -- 4.2 Experiment Details and Evaluation Metrics -- 4.3 Classification Results. ; 4.4 Ablation Study -- 5 Conclusion -- References -- Unsupervised Domain Adaptation Method for Medical Image Segmentation Using Fourier Feature Decoupling and Multi-scale Feature Fusion -- 1 Introduction -- 2 Related Work -- 3 Method Overview -- 3.1 Fourier Transform-Based Feature Decoupling Method -- 3.2 Multi-scale Feature Fusion Strategy -- 3.3 Model Training and Testing -- 4 Experiments -- 4.1 Dataset and Evaluation Metrics -- 4.2 Validation of Model Adaptability in the Target Domain -- 4.3 Ablation Experiment -- 5 Conclusion -- References -- LVMUM: Toward Open-World Object Detection with Large Vision Models and Unsupervised Modeling -- 1 Introduction -- 2 Methodology -- 2.1 Problem Description -- 2.2 SAM-URPG:SAM Unsupervised Region Proposal Generation -- 2.3 ORWM: Object Reconstruction Error Weibull Model -- 3 Experiment -- 3.1 Dataset -- 3.2 Metric -- 3.3 Details -- 3.4 Comparison with State-of-the-Art Models -- 3.5 Ablation Study -- 4 Conclusions -- References -- Implementation and Application of Violence Detection System Based on Multi-head Attention and LSTM -- 1 Introduction -- 2 Related Work -- 2.1 Abnormal Behavior Detection -- 2.2 Violence Detection -- 3 Method -- 3.1 Feature Extraction -- 3.2 Optimization Using Attention Mechanism -- 3.3 Classification -- 4 Experiment and Analysis -- 4.1 Datasets -- 4.2 Experiment -- 4.3 Application -- 5 Conclusion -- References -- GFFNet: An Efficient Image Denoising Network with Group Feature Fusion -- 1 Introduction -- 2 Related Work -- 2.1 Convolutional Neural Network -- 2.2 U-Net Network -- 3 Method -- 3.1 Network Architecture -- 3.2 Group Feature Fusion (GFF) Module -- 3.3 Cross-Information Integration (CII) Module -- 3.4 Network Optimization -- 4 Experiment -- 4.1 Experimental Details -- 4.2 Gaussian Noise Cancellation -- 4.3 Real Image Denoising -- 4.4 Ablation Experiment -- 5 Conclusion. ; References -- End-to-End Object Detection with YOLOF -- 1 Introduction -- 2 Our Approach -- 2.1 Overall Architecture -- 2.2 Stop Gradient -- 2.3 Auxiliary Loss -- 2.4 Semantic Anchor Optimization -- 3 Experients -- 3.1 Baseline Settings -- 3.2 Main Experimental Results -- 3.3 Ablation Experiments -- 3.4 Comparison with Other NMS-Free Detectors -- 4 Conclusion -- References -- BiRGAN: Bi-directional Deep Image Retargeting -- 1 Introduction -- 2 Related Work -- 2.1 Retargeting Dataset -- 3 Retargeting TIReD ++ Dataset -- 4 Approach -- 4.1 BiRGAN Model -- 4.2 Loss Design -- 5 Experiment -- 5.1 Ablation Study -- 5.2 Comparison with Previous Methods -- 5.3 Quantitative Assessment -- 6 Conclusion -- References -- MulTIR: Deep Multi-Target Image Retargeting -- 1 Introduction -- 2 Related Work -- 3 Approach -- 3.1 Formulation -- 3.2 Task Loss -- 3.3 Network Details -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Ablation Study -- 4.3 Performance Comparison -- 5 Conclusion -- References -- PAAM (Parameter-free Attentional Aggregation Model) -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Local Feature Enhancement Module -- 3.2 Global Feature Enhancement Module -- 3.3 Local-Global Feature Interaction Module (L-GFIM) -- 4 Experimental Results -- 4.1 Experimental Details -- 4.2 Experiment Comparing Parameter Count -- 4.3 Image Classification Experiments -- 5 Conclusion -- References -- FRFT Domain Watermarking Algorithm Based on GA Adaptive Optimization -- 1 Introduction -- 2 Main Related Technologies -- 2.1 Discrete Wavelet Transform (DWT) -- 2.2 Singular Value Decomposition (SVD) -- 2.3 Fractional Fourier Transform (FRFT) -- 2.4 Genetic Algorithm (GA) -- 3 Watermark Scheme -- 3.1 Watermark Embedding and Extraction Methods -- 3.2 GA-Based Digital Watermark Algorithm -- 4 Experimental Results and Performance Analysis -- 4.1 Evaluation Indicators. ; 4.2 Solution Performance Analysis and Comparison -- 4.3 Attack Experiment -- 5 Conclusion -- References -- Joint Semantic Feature and Optical Flow Learning for Automatic Echocardiography Segmentation -- 1 Introduction -- 2 Methods -- 2.1 Overview of Framework Workflow -- 2.2 Segmentation Learning -- 2.3 Optical Flow Learning -- 2.4 Cooperation Mechanism and Joint Learning -- 3 Materials -- 3.1 Data -- 3.2 Implementation Details -- 4 Experiment -- 4.1 Evaluation of Introducing Optical Flow Branch -- 4.2 Affection of Training Sample Numbers -- 4.3 Comparison with Existing Methods -- 5 Conclusion -- References -- FMUnet: Frequency Feature Enhancement Multi-level U-Net for Low-Dose CT Denoising with a Real Collected LDCT Image Dataset -- 1 Introduction -- 2 Methods -- 2.1 FMUnet -- 2.2 Frequency Feature Attention (FFA) -- 2.3 Loss Function -- 3 Experiments -- 3.1 Datasets -- 3.2 Implementation Details -- 3.3 Performance Comparisons -- 3.4 Ablation Study -- 4 Discussion -- 5 Conclusion -- References -- Research on Intelligent Recognition Algorithm of Container Numbers in Ports Based on Deep Learning -- 1 Introduction -- 2 Container Number Localization and Recognition Workflow -- 3 Low-Light Enhancement Method Based on Retinex Theory -- 4 Character Super Resolution Reconstruction -- 5 Container Number Localization Method Based on YOLOv5 -- 5.1 MobileNetv3 Module -- 5.2 ECA -- 5.3 Improvements to the YOLOv5 Model -- 5.4 Generating Samples with DCGAN -- 6 Improved CRNN for Container Number Identification -- 7 Experimental Results and Analysis -- 7.1 Dataset -- 7.2 The Improved YOLOv5 Was Used for Experimental Analysis of Container Number Region Positioning -- 7.3 Analysis of the Improved CRNN for Container Number Recognition -- 8 Conclusion and Future Work -- References. ; Dr-SAM: U-Shape Structure Segment Anything Model for Generalizable Medical Image Segmentation -- 1 Introduction -- 2 Method -- 2.1 DrSAM Architecture Design -- 2.2 Training of DrSAM -- 2.3 Inference of DrSAM -- 2.4 Advantages of DrSAM vs. SAM -- 2.5 Advantages of DrSAM vs. MedSAM -- 3 Experiments -- 3.1 Datasets -- 3.2 Performance Comparisons -- 3.3 Ablation Studies -- 4 Conclusion -- References -- Aerial Multi-object Tracking via Information Weighting -- 1 Introduction -- 2 Introduction -- 2.1 Adaptive Weighting -- 2.2 Distribution Feature Extraction -- 2.3 Prediction Box Correction -- 2.4 Spatial-Temporal Feature Enhancement -- 3 Experimental Setup and Results -- 4 Conclusion -- References -- Optimization Method for Fractal Image Compression Based on Self-similarity Evaluation and Gradient Bisection Algorithm -- 1 Introduction -- 2 Related Work -- 2.1 Evaluation of Image Self-similarity -- 2.2 DCT-Based Fractal Coding -- 3 Method -- 3.1 Self-similarity Evaluation Algorithm Based on SSIM -- 3.2 Codebook Classification Based on Low-Frequency Coefficient Statistics -- 3.3 Adaptive Adjustment Methods for Inter-class Thresholds -- 4 Experiment -- 4.1 Data Sets and Evaluation Criteria -- 4.2 Results of Self-similarity Evaluation -- 4.3 Compression Performance Experiments -- 5 Conclusion -- References -- DiffGIC: Diffusion Prior Based Null-Space Correction for High Resolution Grayscale Image Colorization -- 1 Introduction -- 2 Related Work -- 2.1 Grayscale Image Colorization -- 2.2 Text-Driven Diffusion-Based Grayscale Image Colorization -- 2.3 Image Super-Resolution -- 3 DiffGIC -- 3.1 Preliminaries: Range-Null Space Decomposition -- 3.2 Color Image Decomposition for Hierarchical Image Colorization -- 3.3 Null-Space Diffusion Prior for Color Information Correction -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Experiment Setup. ; 4.3 Comparing with SR-HIPS-Based Methods.
• Sommario/riassunto: This 13-volume set LNCS 14862-14874 constitutes - in conjunction with the 6-volume set LNAI 14875-14880 and the two-volume set LNBI 14881-14882 - the refereed proceedings of the 20th International Conference on Intelligent Computing, ICIC 2024, held in Tianjin, China, during August 5-8, 2024. The total of 863 regular papers were carefully reviewed and selected from 2189 submissions. This year, the conference concentrated mainly on the theories and methodologies as well as the emerging applications of intelligent computing. Its aim was to unify the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications. Therefore, the theme for this conference was "Advanced Intelligent Computing Technology and Applications". Papers that focused on this theme were solicited, addressing theories, methodologies, and applications in science and technology.
• Titolo autorizzato: Advanced Intelligent Computing Technology and Applications
• ISBN: 981-9756-00-6
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910878055803321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture Notes in Computer Science, . 1611-3349 ; ; 14868