Neural Information Processing

Name: Neural Information Processing | 30th International Conference, ICONIP 2023, Changsha, China, November 20-23, 2023, Proceedings, Part IV
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

30th International Conference, ICONIP 2023, Changsha, China, November 20-23, 2023, Proceedings, Part IV

Biao Luo Long Cheng Zheng-Guang Wu Hongyi Li Chaojie Li(Herausgeber*in)

Springer (Verlag)

Erschienen am 14. November 2023

XX, 577 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-981-99-8070-3 (ISBN)

96,29 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents - Part IV
Human Centred Computing
Cross-Modal Method Based on Self-Attention Neural Networks for Drug-Target Prediction
1 Instructions
2 Materials and Approaches
2.1 Benchmark Datasets
2.2 Implementation Process of SANN-DTI
2.3 Adjustment of Parameters
2.4 Evaluation Metrics
3 Experimental Results
3.1 Compared with Baseline Models
3.2 Impact of Each Component on Predicted Performance
4 Case Study
5 Conclusion
References
GRF-GMM: A Trajectory Optimization Framework for Obstacle Avoidance in Learning from Demonstration
1 Introduction
2 Problem Statement
3 Method
3.1 Gaussian Mixture Model/Gaussian Mixture Regression
3.2 Optimization Algorithm: GRF-GMM
4 Simulations and Experiments
4.1 2D Handwriting Letter Task
4.2 Experiment
4.3 Comparisons
5 Conclusions
References
SLG-NET: Subgraph Neural Network with Local-Global Braingraph Feature Extraction Modules and a Novel Subgraph Generation Algorithm for Automated Identification of Major Depressive Disorder
1 Introduction
2 Related Work
2.1 Construction of Braingraph
3 Method
3.1 Sub-braingraph Sampling and Encoding
3.2 Sub-braingraph Selection and Sub-braingraph's Node Selection by LFE Module
3.3 Sub-braingraph Sketching by GFE Module and Classification
4 Experiments
4.1 Dataset and Parameters Setting
4.2 Overall Evaluation
4.3 S-BFS, LFE, and GFE Modules Analysis
5 Conclusion
References
CrowdNav-HERO: Pedestrian Trajectory Prediction Based Crowded Navigation with Human-Environment-Robot Ternary Fusion
1 Introduction
2 Related Work
2.1 Socially Aware Crowded Navigation
2.2 Simulator for Crowded Navigation
3 Problem Formulation
4 HRO Ternary Fusion Simulator
4.1 Simulator Setting
4.2 Static Environment Construction and Collision Avoidance
4.3 Crowd Interaction Optimization
5 A Crowded Navigation Framework with HERO Ternary Feature Fusion
5.1 Spatial-Temporal Pedestrian Trajectory Prediction
5.2 Dual-Channel Value Estimation Network
6 Experiments
6.1 Experimental Settings
6.2 Quantitative Evaluations for Crowded Navigation
6.3 Quantitative Evaluation of Impact of Environment on Navigation
6.4 Quantitative Evaluations on Real Pedestrian Dataset
7 Conclusion
References
Modeling User's Neutral Feedback in Conversational Recommendation
1 Introduction
2 Related Work
3 Problem Definition
4 Proposed Methods
4.1 Representation Learning
4.2 Action Decision
4.3 Selection Strategies
4.4 Update and Deduction
5 Experiments
5.1 DataSet
5.2 Experimental Settings
5.3 Performance Comparison of NFCR with Existing Models (RQ1)
5.4 Ablation Studies (RQ2)
5.5 Case Study on Neutral Feedback (RQ3)
6 Conclusions
References
A Domain Knowledge-Based Semi-supervised Pancreas Segmentation Approach
1 Introduction
2 Related Work
2.1 Semi-supervised Medical Image Segmentation
2.2 Domain Knowledge
3 Methodology
3.1 Loss Function
4 Experiments and Results
4.1 Datasets
4.2 Implementation Details
4.3 Ablation Study
4.4 Comparison Study
5 Conclusion
References
Soybean Genome Clustering Using Quantum-Based Fuzzy C-Means Algorithm
1 Introduction
2 Preliminaries
2.1 Fuzzy C-Means
2.2 Quantum Computing Concept
3 Proposed Work
3.1 Dataset Preparation
3.2 Quantum Fuzzy C-Means (QFCM) Clustering Approach
4 Experiment and Result
4.1 Experimental Environment
4.2 Datasets Description
4.3 Performance Evaluation
4.4 Results and Discussion
5 Conclusion
References
DAMFormer: Enhancing Polyp Segmentation Through Dual Attention Mechanism
1 Introduction
2 Related Work
2.1 Polyp Segmentation
2.2 Attention Mechanism
3 Proposed Method
3.1 Transformer Encoder
3.2 ConvBlock
3.3 Enhanced Dual Attention Module
3.4 Channel-Wise Scaling
3.5 Effective Feature Fusion
4 Experiments
5 Conclusion
References
BIN: A Bio-Signature Identification Network for Interpretable Liver Cancer Microvascular Invasion Prediction Based on Multi-modal MRIs
1 Introduction
2 Related Works
2.1 MVI Prediction Models Based on MRIs
2.2 MVI Interpretable Deep Models
3 The Proposed Multi-modal Fusion Based BIN Method
4 Experiment and Analysis
4.1 Performance Comparisons
4.2 Qualitative Experiment
5 Conclusion
References
Human-to-Human Interaction Detection
1 Introduction
2 Related Work
3 HID Task
3.1 Problem Definition
3.2 Evaluation Metrics
3.3 The AVA-Interaction Dataset
4 SaMFormer
4.1 Visual Feature Extractor
4.2 The Split Stage
4.3 The Merging Stage
4.4 Training and Inference
5 Experiments
5.1 Main Results on AVA-I
5.2 Ablation Study
5.3 Qualitative Results
5.4 Evaluation on BIT and UT
6 Conclusion
References
Reconstructing Challenging Hand Posture from Multi-modal Input
1 Introduction
2 Related Work
3 Capture
4 Skeleton-Shape Alignment
5 Data Evaluation and Applications
6 Conclusions and Future Work
References
A Compliant Elbow Exoskeleton with an SEA at Interaction Port
1 Introduction
2 Mechanical Design
2.1 Exoskeleton Design
2.2 SEA Analysis
3 SEA Modeling
3.1 NARMAX Model
3.2 T-S Fuzzy Model
3.3 LSTM Model
3.4 Model Training
3.5 Model Validation
4 Exoskeleton Flexible Control
5 Conclusion
References
Applications
Differential Fault Analysis Against AES Based on a Hybrid Fault Model
1 Introduction
2 DFA on AES State
2.1 Proposed Fault Model
2.2 The Analysis of Cracking AES
2.3 The Process of Cracking AES
3 Experimental Results and Comparisons
4 Conclusions
References
Towards Undetectable Adversarial Examples: A Steganographic Perspective
1 Introduction
2 Related Works
2.1 Adversarial Attack
2.2 Embedding Suitability Map
3 Proposed Scheme
3.1 Motivation
3.2 Embedding Suitability Map-Weighted Attack
3.3 Combination with CAM
4 Experimental Results
4.1 Attack Ability
4.2 Undetectability
4.3 Undetectability-Attack Ability Tradeoff
4.4 Visual Quality
5 Conclusion
References
On Efficient Federated Learning for Aerial Remote Sensing Image Classification: A Filter Pruning Approach
1 Introduction
2 Related Work
2.1 Efficient Federated Learning
2.2 Filter Pruning
3 Methodology
3.1 System Model
3.2 Cross-All-Layers Importance Measure for Pruning
3.3 CALIM-FL Work Process
4 Experiments and Results
4.1 Experimental Settings
4.2 Result Discussion
5 Conclusion
References
ASGNet: Adaptive Semantic Gate Networks for Log-Based Anomaly Diagnosis
1 Introduction
2 Related Work
3 The Proposed Model
3.1 Task Description
3.2 Definition of Terms
3.3 Log Statistics Information Representation
3.4 Log Deep Semantic Representation
3.5 Adaptive Semantic Threshold Mechanism
4 Experimental Setup
4.1 Dataset and Hyper-parameters
4.2 Training and Hyperparameters
5 Experimental Results
5.1 Model Comparisons (RQ1)
5.2 Ablation Study (RQ2)
5.3 Parameter Sensitivity (RQ3)
6 Conclusion
References
Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning
1 Introduction
2 Related Work
3 Proposed Method
3.1 Prophetic Teacher Learning
3.2 Propheter-Guided Long-Tailed Classification
4 Experiments
4.1 Datasets and Implementation Details
4.2 Experimental Results
4.3 Ablation Study
5 Conclusions
References
Sequential Transformer for End-to-End Person Search
1 Introduction
2 Method
2.1 SeqTR Architecture
2.2 re-ID Transformer
2.3 Training and Inference
3 Experiments
3.1 Datasets and Settings
3.2 Implementation Details
3.3 Comparison to the State-of-the-arts
3.4 Ablation Study
4 Conclusion
References
Multi-scale Structural Asymmetric Convolution for Wireframe Parsing
1 Introduction
2 Methodology
2.1 Overall Network Architecture
2.2 Customized Backbone
2.3 Geometry Proposal Network
3 Experiments
3.1 Datasets and Metrics
3.2 Implementation Details
3.3 Ablation Study
3.4 Comparison with Other Methods
4 Conclusions
References
S3ACH: Semi-Supervised Semantic Adaptive Cross-Modal Hashing
1 Introduction
2 Related Works
3 The Proposed Method
3.1 Notation and Problem Formulation
3.2 S3ACHMethod
3.3 Optimization
3.4 Hash Function Learning
3.5 Time Cost Analysis
4 Experiments
4.1 Datasets
4.2 Compared Baselines and Evaluation Metrics
4.3 Implementation Details
4.4 Results
4.5 Ablation Experiments
4.6 Parameter Sensitivity Analysis
4.7 Convergence Analysis
5 Conclusion
References
Intelligent UAV Swarm Planning Based on Undirected Graph Model
1 Introduction
2 Methods
2.1 Improved MINCO Algorithm
2.2 UAV Cluster Modeling
3 Constraints in Cost Functions
3.1 Smoothness Penalty
3.2 Total Time Penalty
3.3 Collision Penalty
3.4 Cluster Formation Penalty
3.5 Penalty for Collisions Between Unmanned Aerial Vehicles
3.6 Dynamic Feasibility Penalty
3.7 Penalty for Uniform Distribution of Constraint Points
4 Results and Discussion
4.1 Experimental Environment
4.2 Experimental Analysis
5 Conclusion and Future
References
Learning Item Attributes and User Interests for Knowledge Graph Enhanced Recommendation
1 Introduction
2 Problem Formalization
3 Methodology
3.1 Model Overview
3.2 Attribute Modeling Layer
3.3 Attribute Propagation Layer
3.4 Interest-Aware Attention Layer
3.5 Model Optimization
4 Experiments
4.1 Experimental Settings
4.2 Performance Comparison (RQ1)
4.3 Study of AKGAN (RQ2)
4.4 Case Study (RQ3)
5 Related Work
6 Conclusion
References
Multi-view Stereo by Fusing Monocular and a Combination of Depth Representation Methods
1 Introduction
2 Related Work
2.1 Multi-view Depth Estimation Based on Monocular Assistance
2.2 Regression and Classification MVS Methods
3 Methods
3.1 Inherited MVS Pipeline
3.2 MVS Assisted by Monocular Depth Estimation
3.3 Collaboration of Regression and Classification
3.4 Distribution Consistency
4 Implementation and Result
4.1 Implementation
4.2 Results on DTU Benchmark
4.3 Results on Tanks and Temples Benchmark
4.4 Ablation Studies
5 Conclusion
References
A Fast and Scalable Frame-Recurrent Video Super-Resolution Framework
1 Introduction
2 Related Work
3 Method
3.1 Frame-Recurrent Part
3.2 Super-Resolution Flow Net (SRFNet)
3.3 Recurrent-Residual Part
3.4 Loss Functions
4 Experiments
4.1 Datasets
4.2 Implementation Details
4.3 Ablation Experiment
4.4 Comparison with Other Methods
5 Conclusion
References
Structural Properties of Associative Knowledge Graphs
1 Introduction
2 Structural Associative Knowledge Graphs
3 Gradual Increase in the Knowledge Graph Density
4 Dependence on the Size of the Context
4.1 Critical Graph Density
4.2 Finding the Maximum Memory Capacity
4.3 Algorithm for Scene Retrieval
5 Experiments
5.1 Randomly Generated Scenes
5.2 Iris Data
5.3 Scene Recognition Using Deep Neural Networks
6 Conclusions
References
Nonlinear NN-Based Perturbation Estimator Designs for Disturbed Unmanned Systems
1 Introduction
2 Preliminaries
2.1 Dynamics of the Unmanned System
2.2 Radial Basis Function Neural Networks
2.3 Objectives
3 Nonlinear NN-Based Dynamic Estimator Designs
4 Simulation Examples
4.1 Unmanned Marine Systems
4.2 A Quadrotor System
5 Conclusion
References
DOS Dataset: A Novel Indoor Deformable Object Segmentation Dataset for Sweeping Robots
1 Introduction
2 Related Work
2.1 Detection and Segmentation Datasets
2.2 Detection and Segmentation Methods
3 DOS Dateset
3.1 Data Collection
3.2 Data Annotation
3.3 Dataset Description
4 Experiments
5 Conclusion
References
Leveraging Sound Local and Global Features for Language-Queried Target Sound Extraction
1 Introduction
2 Proposed Method
2.1 Framework
2.2 Linguistic-Acoustic (LA) Fusion Module
2.3 Language-Aware Dynamic Block (LADB)
2.4 Local and Global Operation Submodules
3 Experimental Setup
3.1 Dataset
3.2 Training Parameters
3.3 Evaluation Metrics
4 Results and Analysis
4.1 Model Comparison
4.2 Ablation Study
5 Conclusion
References
PEVLR: A New Privacy-Preserving and Efficient Approach for Vertical Logistic Regression
1 Introduction
2 Related Work
3 Preliminaries
3.1 Logistic Regression
3.2 SGD and Variance-Reduced Variants
3.3 Random Matrix Sketch
4 Solution
4.1 Problem Formulation
4.2 Algorithm
5 Experiments
5.1 Experimental Settings and Evaluation Metric
5.2 Results and Discussion
6 Conclusion
References
Semantic-Pixel Associative Information Improving Loop Closure Detection and Experience Map Building for Efficient Visual Representation
1 Introduction
2 Related Work
3 Methodology
3.1 Revisiting RatSLAM
3.2 Semantic-Pixel Associative RatSLAM
3.3 Integrate Semantic Information in LCD
3.4 Experience Map Building with Semantics
4 Experimental Analysis
4.1 Datasets
4.2 Performance Comparison of LCD
4.3 Performance Trade-Offs for LCD
4.4 Brightness Transformation on LCD
4.5 Experience Map Building on Lab Dataset
5 Conclusion
References
Knowledge Distillation via Information Matching
1 Introduction
2 Related Work
2.1 Knowledge Distillation
2.2 Receptive Field
3 Method
3.1 Preliminaries
3.2 Effective Receptive Field Calculation
3.3 Feature Matching Distillation
4 Experiments
4.1 Datasets and Experiments Configuration
4.2 Compared to Different Distillation Methods
4.3 Visualization
4.4 Ablation
5 Conclusion
References
CenAD: Collaborative Embedding Network for Anomaly Detection with Leveraging Partially Observed Anomalies
1 Introduction
2 Related Work
2.1 Traditional Anomaly Detection with Observed Anomalies
2.2 Deep Anomaly Detection with Observed Anomalies
3 CenAD
3.1 Problem Statement
3.2 Overview
3.3 Deep Autoencoder
3.4 Collaborative Learning
3.5 Anomaly Detection Using CenAD
4 Experiments
4.1 Datasets
4.2 Comparative Methods
4.3 Parameters Settings
4.4 Metrics
4.5 Effectiveness Tests w.r.t. Numbers of Covered Anomaly Distributions
4.6 Effectiveness Tests w.r.t. Proportions of Partially Observed Anomalies
4.7 Effectiveness Tests w.r.t. Uncovered Anomalies and Covered Anomalies
4.8 Ablation Study
5 Conclusion
References
PAG: Protecting Artworks from Personalizing Image Generative Models
1 Introduction
2 Literature Review
3 Theoretical Motivations
4 Main Method
4.1 Overall Framework
4.2 Generate Semantically Abnormal Samples
5 Experiments
5.1 Human Evaluation Results
5.2 Qualitative Protection Performance
5.3 Ablation Study
6 Conclusion
References
Attention Based Spatial-Temporal Dynamic Interact Network for Traffic Flow Forecasting
1 Introduction
2 Related Works
3 Methodology
3.1 Preliminaries
3.2 Attention Based Spatial-Temporal Dynamic Interact Network
3.3 Prediction Layer and Loss Function
4 Experiments
4.1 Experimental Setup
4.2 Experimental Results
4.3 Ablation Experiments
5 Conclusion
References
Staged Long Text Generation with Progressive Task-Oriented Prompts
1 Introduction
2 Related Work
3 Methodology
3.1 Framework Overview
3.2 Keyphrases Uncompression Stage
3.3 Transition Paraphrase Stage
3.4 Final Generation Stage
4 Experimental Setups
4.1 Tasks and Datasets
4.2 Baselines and Comparisons
5 Results and Analysis
5.1 Automatic Evaluation
5.2 Human Evaluation
5.3 Sketch with Elastic Mask Tokens
5.4 Knowledge Prompt
5.5 Sample Outputs
6 Conclusion
References
Learning Stable Nonlinear Dynamical System from One Demonstration
1 Introduction
2 Problem Formulation
3 Proposed Approach
4 Experiment Results and Discussions
4.1 Learning from One Demonstration
4.2 Validation on Robot
5 Conclusions
References
Towards High-Performance Exploratory Data Analysis (EDA) via Stable Equilibrium Point
1 Introduction
2 Preliminary
2.1 Spectral Clustering Algorithm
2.2 t-Distributed Stochastic Neighbor Embedding
3 Methods
3.1 Algorithm Complexity
4 Experiment
4.1 Data Sets
4.2 Compared Methods
4.3 Experimental Results of Spectral Clustering
4.4 Experimental Results of t-SNE
5 Conclusion
6 Contributions
References
MVFAN: Multi-view Feature Assisted Network for 4D Radar Object Detection
1 Introduction
2 Related Works
3 Methodology
3.1 Overview
3.2 Multi-view Feature Extraction
3.3 Radar Feature Assisted Backbone
3.4 Detection Head and Loss Function
4 Experiments
4.1 Dataset
4.2 Evaluation
4.3 Implementation Details
4.4 Experiment Results
4.5 Ablation Study
5 Conclusion
References
Time Series Anomaly Detection with a Transformer Residual Autoencoder-Decoder
1 Introduction
2 Related Work
3 Problem Formulation
4 Methodology
4.1 Multi-interval Sampling
4.2 TRAD-Based Prediction
4.3 Anomaly Detection
5 Experiments Setup
5.1 Datasets
5.2 Baselines
5.3 Implementation
6 Experiment Results
6.1 Ablation Study
7 Conclusion
References
Adversarial Example Detection with Latent Representation Dynamic Prototype
1 Introduction
2 Related Work
3 Methodology
3.1 Overview
3.2 Random Homogeneous Sampling
3.3 Latent Representation Dynamic Prototype
3.4 Adversarial Discriminator
4 Experiments
4.1 Experiment Setup
4.2 Threat Model
4.3 Comparison in Seen Attacks
4.4 Comparison in Unseen Attacks
4.5 Time Comparison
5 Conclusion
References
A Multi-scale and Multi-attention Network for Skin Lesion Segmentation
1 Introduction
2 Method
2.1 Network Architecture
2.2 FLA
2.3 Multi-attention Decoder
3 Experiments
3.1 Dataset
3.2 Implementation Details and Evaluation Metrics
3.3 Loss Function
3.4 Comparison with the State-of-the-Arts
3.5 Ablation Experiment
4 Conclusion
References
Temporal Attention for Robust Multiple Object Pose Tracking
1 Introduction
2 Related Work
3 Method
3.1 Overview
3.2 Temporal Correlation Decoder
3.3 Pose Estimation Decoder
4 Experiments
4.1 Experimental Settings
4.2 Results
4.3 Ablation Study
5 Conclusion
References
Correlation Guided Multi-teacher Knowledge Distillation
1 Introduction
2 Related Work
3 Method
3.1 Knowledge Distillation Paradigm
3.2 Intermediate Feature Correlation Guidance
3.3 Prediction Vector Correlation Guidance
4 Experiments
4.1 Experimental Setup
4.2 Experimental Results on CIFAR-10
4.3 Experimental Results on CIFAR-100
4.4 Ablation Study
5 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken