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.

Format:

Book

Author/Creator:

Huang, De-Shuang.

Contributor:

Chen, Wei.

Pan, Yijie.

Series:

Lecture Notes in Computer Science, 1611-3349 ; 14869

Language:

English

Subjects (All):

Computational intelligence.

Machine learning.

Computer networks.

Application software.

Computational Intelligence.

Machine Learning.

Computer Communication Networks.

Computer and Information Systems Applications.

Local Subjects:

Computational Intelligence.

Machine Learning.

Computer Communication Networks.

Computer and Information Systems Applications.

Physical Description:

1 online resource (525 pages)

Edition:

1st ed. 2024.

Place of Publication:

Singapore : Springer Nature Singapore : Imprint: Springer, 2024.

Summary:

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. .

Contents:

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

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

Fusion of Saliency and Edge Map for Multi-operator Image Retargeting Algorithm

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

MOD-YOLO: Improved YOLOv5 Based on Multi-softmax and Omni-Dimensional Dynamic Convolution for Multi-label Bridge Defect Detection

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

Color Image Steganography Based on Two-Channel Preprocessing and U-Net Network

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

Application of a Hybrid Particle Image Velocimetry Method Based on Window Function in the Field of Turbulence

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

Semantics-Enhanced Refiner in Skip Connection for Crack Segmentation

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

Refinement Correction Network for Scene Text Detection

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

4.4 Comparative Experiment

Weight Uncertainty Network for Low-Light Image Enhancement

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

4.1 Experimental Settings

4.2 Comparison with State-of-the-Arts

Unsupervised Extremely Low-Light Image Enhancement with a Laplacian Pyramid Network

3 Unsupervised Extremely Low-Light Image Enhancement with a Laplacian Pyramid Network

3.1 Motivations

3.2 Networks

3.3 Loss Functions

4.1 Datasets and Training Details

4.2 Baselines and Evaluation Metrics

4.3 Comparing to State-of-the-Arts

4.4 Ablation Study

A Multimodal Fake News Detection Model with Self-supervised Unimodal Label Generation

2.1 Unimodal Fake News Detection

2.2 Multimodal Fake News Detection

3.1 Feature Extraction Module

3.2 Multimodal Feature Fusion

3.3 Unimodal Label Generation

3.4 Model Optimization and Prediction

4.1 Experimental Configurations

4.2 Overall Performance

Image Denoising Based on an Improved Wavelet Threshold and Total Variation Model

2 Preliminaries

2.1 Analysis of Lung CT Image Features

2.2 TV Framework

2.3 Wavelet Threshold Denoising

3.1 Improved Thresholding Function

3.2 Proposed Method

4 Experimental Results and Analysis

References.

A Two-Stage Coupled Learning Network for Image Deblurring

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

Palmprint Recognition Using SC-LNMF Model in Gabor Domain

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

4.1 Test Data Preprocessing

4.2 Learning Feature Bases

4.3 Representation of Test Images

4.4 Recognition Results of Palmprint Images

SkinDiff: A Novel Data Synthesis Method Based on Latent Diffusion Model for Skin Lesion Segmentation

2.1 Skin Lesion Segmentation

2.2 Diffusion Model

3 Methods

3.1 Generating Foreground Stage

3.2 Outpainting Background Stage

4.1 Dataset

4.2 Evaluation Metrics

4.3 Implementation Details

4.4 Evaluations and Analyses

MFAAnet: New Feature Extraction Network in Image Super-Resolution

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

Context-Aware Relative Distinctive Feature Learning for Person Re-identification

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

Image Captioning with Masked Diffusion Model

3.1 Features Fusion

3.2 Masked Diffusion

3.3 Embedding and Rounding

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

Textile Defect Detection Based on Multi-proportion Spatial Pyramid Convolution and Adaptive Multi-scale Feature Fusion

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

Real-Time Detection of Multi-scale Traffic Signs Based on Decoupled Heads

2.1 Traffic-Signs Recognition

2.2 Small Object Detection

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

LAROD-HD: Low-Cost Adaptive Real-Time Object Detection for High-Resolution Video Surveillance

2.1 Small Object Detection.

2.2 Object Detection on High-Resolution Images.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

981-9756-03-0

OCLC:

1451462276