Anmerkung: Intro -- Preface -- Organization -- Contents - Part II -- AI Ethics, Privacy, Fairness and Security -- Saliency Map-Based Local White-Box Adversarial Attack Against Deep Neural Networks -- 1 Introduction -- 2 Related Work -- 2.1 Model Interpretability Methods -- 2.2 White-Box Adversarial Attack Methods -- 3 Proposed Approach -- 3.1 Selecting Important Area by Saliency Map -- 3.2 Combining Saliency Map with Single-Step Attack Method -- 3.3 Combining Saliency Map and Iterative Attack Method -- 4 Experiments -- 4.1 Datasets and Networks -- 4.2 Evaluation Indexes -- 4.3 Hyperparameters -- 4.4 Experimental Result -- 5 Conclusion -- References -- Improving Adversarial Attacks with Ensemble-Based Approaches -- 1 Introduction -- 2 Related Works -- 2.1 Optimization-Based Methods -- 2.2 Gradient-Based Methods -- 2.3 Targeted Attacks -- 3 Methodology -- 3.1 Motivation -- 3.2 Ensemble Schemes -- 3.3 Gradient Descent Mechanisms -- 3.4 Optimization Algorithm -- 4 Experimental Results -- 4.1 Experimental Settings -- 4.2 Attacking a Single Model -- 4.3 Attacking an Ensemble of Models -- 5 Conclusion and Future Work -- References -- Applications of Artificial Intelligence -- Browsing Behavioral Intent Prediction on Product Recommendation Pages of E-commerce Platform -- 1 Introduction -- 2 Related Work -- 2.1 Browsing Behavior Analysis -- 2.2 Browsing Behavioral Intent Prediction -- 3 Methodology -- 4 Experiments -- 4.1 Data Collection and Processing -- 4.2 Model Architecture -- 4.3 Interest Analysis Method -- 5 Results and Discussion -- 5.1 Prediction Results -- 5.2 Interest Analysis Results and Discussion -- 6 Conclusion -- References -- An Optical Satellite Controller Based on Diffractive Deep Neural Network -- 1 Introduction -- 2 Methods -- 2.1 Problem Formulation -- 2.2 Optical Controller Framework -- 2.3 Architecture of the Optical Controller. , 2.4 Optimization of the Optical Controller -- 3 Experiments -- 3.1 Dataset Description -- 3.2 Experimental Settings -- 3.3 Experimental Results -- 4 Conclusion -- References -- Incomplete Cigarette Code Recognition via Unified SPA Features and Graph Space Constraints -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Features Extraction Using FPN -- 3.2 Instance Segmentation via Unified SPA Features -- 3.3 Landmark Estimation via Graph Space Constraints -- 3.4 Text Regularization -- 3.5 Loss Function -- 4 Experiments -- 4.1 Evaluation of Instance Segmentation -- 4.2 Performance of Landmark Estimation -- 4.3 End-to-End Performance -- 4.4 Ablation Experiments -- 5 Conclusion -- References -- A Large-Scale Tobacco 3D Bin Packing Model Based on Dual-Task Learning of Group Blocks -- 1 Introduction -- 2 Problem Formulation -- 3 Method -- 3.1 Group Block Generation Algorithm -- 3.2 Dual-Task Learning of Group Blocks -- 4 Experiment -- 5 Conclusions -- References -- ETH-TT: A Novel Approach for Detecting Ethereum Malicious Accounts -- 1 Introduction -- 2 ETH Tracking Tree Method -- 2.1 ETH Tracking Tree and Traceability Rate -- 2.2 Features Extraction -- 2.3 Model Design -- 3 Experiment -- 3.1 Dataset -- 3.2 Experimental Details -- 3.3 Experimental Result -- 3.4 Result Analysis -- 4 Availability of Data and Material -- References -- Multi-objective Meta-return Reinforcement Learning for Sequential Recommendation -- 1 Introduction -- 2 Related Works -- 3 Preliminaries -- 4 Approach -- 4.1 M2OR-RL Framework -- 4.2 Optimization -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Experiment with Multiple Objectives -- 5.3 Experiment with Single Objective -- 6 Conclusion -- A Algorithms -- A.1 Implementation Detail -- A.2 Implementation Details -- References -- Purchase Pattern Based Anti-Fraud Framework in Online E-Commerce Platform Using Graph Neural Network. , 1 Introduction -- 2 Related Work -- 2.1 Fraud Detection -- 2.2 Graph Representation Learning -- 3 Proposed Method -- 3.1 Dynamic Purchase Pattern (DPP) -- 3.2 GNN with Similarity and Relation (GSR) -- 4 Experiments -- 4.1 Dataset -- 4.2 Purchase Pattern Visualization -- 4.3 Fraudulent Order Detection Result of GSR -- 5 Conclusions and Future Work -- References -- Physical Logic Enhanced Network for Small-Sample Bi-layer Metallic Tubes Bending Springback Prediction -- 1 Introduction -- 2 Background Knowledge -- 2.1 RDB Processing of BMT -- 2.2 Equivalent Section Theory -- 3 Methodology -- 3.1 Proposed Prediction Architecture -- 3.2 Preliminary Analysis of BMT Equivalence Section -- 3.3 Composition of the Loss Function -- 4 Case Study -- 4.1 Dataset Construction -- 4.2 Precision Analysis of Proposed Method -- 4.3 Effectiveness of PE-NET -- 5 Conclusion -- References -- Blind Surveillance Image Quality Assessment via Deep Neural Network Combined with the Visual Saliency -- 1 Introduction -- 2 Proposed Method -- 2.1 Saliency-Based Local Region Selection -- 2.2 Quality-Aware Feature Extraction -- 2.3 Quality Prediction -- 3 Experiments -- 3.1 Test Database -- 3.2 The Effect of Visual Quality on IVSS -- 3.3 Performance Comparison with SOTA BIQA Methods -- 4 Conclusion -- References -- Power Grid Bus Cluster Based on Voltage Phasor Trajectory -- 1 Introduction -- 2 Propagation Mechanism of Power Grid Faults -- 3 Trajectory-Based Similarity -- 3.1 Length of Trajectory -- 3.2 Curvature of Trajectory -- 3.3 Topological Distance -- 3.4 Similarity of Trajectories -- 3.5 Power Grid Bus Cluster -- 4 Experiments -- 4.1 Visualize for Each Dimension -- 4.2 Trajectory Similarity Analysis -- 4.3 Trajectory Cluster Analysis -- 5 Conclusion -- References -- Following the Lecturer: Hierarchical Knowledge Concepts Prediction for Educational Videos -- 1 Introduction. , 2 Related Work -- 3 Preliminaries -- 3.1 Problem Definition -- 3.2 Text-Visual Uniform Section Segmentation -- 4 Spotlight Flow Network -- 4.1 Multimodal Representation Layer -- 4.2 Hierarchical Multi-label Inter-level Constrained Classifier -- 4.3 Training SFNet -- 5 Experiments -- 5.1 Data Description -- 5.2 Baseline Approaches and Experimental Setup -- 5.3 Experimental Results -- 6 Conclusion -- References -- Learning Evidential Cognitive Diagnosis Networks Robust to Response Bias -- 1 Introduction -- 2 Method -- 2.1 Problem Definition -- 2.2 Evidential Cognitive Diagnosis Model -- 2.3 Uncertainty-ASSIST (UncASSIST) Dataset -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Main Results on the UncASSIST Dataset -- 3.3 Analysis of the Uncertainty Estimation -- 4 Conclusion -- References -- An Integrated Navigation Method for UAV Autonomous Landing Based on Inertial and Vision Sensors -- 1 Introduction -- 2 Landing Process Analysis and Scheme Design -- 3 Intelligent Identification of Airport Runway Based on Deep Learning Semantic Segmentation -- 3.1 Runway Segmentation Network Design -- 3.2 Runway Edge Feature Extraction -- 4 Modeling of Visual Relative Position/Attitude Measurement Based on the Characteristics of Runway Boundary -- 4.1 Coordinate System and Parameters Definition -- 4.2 Mathematical Modeling of Visual Relative Position/Attitude Measurement -- 5 Information Fusion Model of Inertial/Visual Sensor -- 5.1 System State Equation -- 5.2 System Observation Equation -- 6 Experiment Verification -- 6.1 Experiment Conditions -- 6.2 Experiment Results -- 7 Conclusion -- References -- An Automatic Surface Defect Detection Method with Residual Attention Network -- 1 Introduction -- 2 Proposed Methodology -- 2.1 Overview of Network Framework -- 2.2 Backbone Network -- 2.3 MCF Block -- 3 Experiment Data and Preprocessing -- 3.1 Data Set. , 3.2 Image Preprocessing -- 4 Experiment Results and Analysis -- 4.1 Implementation Details -- 4.2 Ablation Study -- 4.3 Performance Comparison -- 5 Conclusion -- References -- Research on Intelligent Decision-Making Irrigation Model of Water and Fertilizer Based on Multi-source Data Input -- 1 Introduction -- 2 Materials and Methods -- 2.1 Data Acquisition -- 2.2 Identification of Influencing Factors and Coupling Verification -- 3 Intelligent Decision-Making Irrigation Model of Water and Fertilizer -- 4 Results and Discussion -- 4.1 Comparison of Prediction Performance of Different Models -- 4.2 Analysis of Factors Affecting the Prediction Performance of the Model -- 4.3 Prediction Error Analysis of Water and Fertilizer Irrigation Quantity -- 4.4 Model Stability Analysis -- 5 Conclusion -- References -- Interaction-Aware Temporal Prescription Generation via Message Passing Neural Network -- 1 Introduction -- 2 Related Work -- 2.1 Recurrent Neural Network for Healthcare -- 2.2 Drug Recommendation -- 3 Preliminaries -- 3.1 Dataset -- 3.2 Problem Formulation -- 4 Technical Details -- 4.1 Patient Encoder -- 4.2 Prescription Generator -- 5 Experiments -- 5.1 Experimental Settings -- 5.2 Results and Analyses -- 6 Conclusion -- References -- Adversarial and Implicit Modality Imputation with Applications to Depression Early Detection -- 1 Introduction -- 2 Proposed Method -- 2.1 Learning Multi-modal Representations via Auto-encoding -- 2.2 Adversarial and Implicit Modality Imputation (AIMI) -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Comparisons on Robust Multi-modal Depression Diagnosis -- 3.3 Advantages on Modality Imputation and Representation -- 4 Conclusion -- References -- EdgeVR360: Edge-Assisted Multiuser-Oriented Intelligent 360-degree Video Delivery Scheme over Wireless Networks -- 1 Introduction -- 2 Related Works -- 2.1 360-degree Video. , 2.2 DRL-Based 360-degree Video Delivery.

Anmerkung: Intro -- Preface -- Organization -- Contents - Part III -- Intelligent Multilingual Information Processing -- A New Method for Assigning Hesitation Based on an IFS Distance Metric -- 1 Introduction -- 2 Preparatory Knowledge -- 2.1 Intuitionistic Fuzzy Sets -- 2.2 Intuitionistic Fuzzy Set Distance Metric -- 3 Existing Intuitionistic Fuzzy Set Distance Metrics and Their Analysis -- 3.1 Existing Intuitionistic Fuzzy Set Distance Metric -- 3.2 Existing Intuitionistic Fuzzy Set Distance Analysis -- 4 A New Intuitionistic Fuzzy Set Distance Metric -- 5 Example Analysis -- 6 Concluding Remarks -- References -- Adaptive Combination of Filtered-X NLMS and Affine Projection Algorithms for Active Noise Control -- 1 Introduction -- 2 FxNLMS and FxAP Algorithms in ANC System -- 2.1 Framework of ANC -- 2.2 FxNLMS and FxAP Algorithms -- 3 Combined FxNLMS and FxAP Algorithm -- 4 Simulation Results -- 5 Conclusion -- References -- Linguistic Interval-Valued Spherical Fuzzy Sets and Related Properties -- 1 Introduction -- 2 Preliminaries -- 2.1 Spherical Fuzzy Sets -- 2.2 Interval-Valued Spherical Fuzzy Sets -- 2.3 Linguistic Term Sets -- 2.4 Linguistic Spherical Fuzzy Sets -- 3 Linguistic Interval-Valued Spherical Fuzzy Sets -- 3.1 Concepts of LIVSFS and LIVSFN -- 3.2 Basic Operations and Properties of LIVSFS -- 3.3 Basic Operations and Properties of LIVSFN -- 3.4 Comparing Methods and Measurement Formulas of LIVSFNs -- 4 Conclusion -- References -- Knowledge Representation and Reasoning -- A Genetic Algorithm for Causal Discovery Based on Structural Causal Model -- 1 Introduction -- 2 Related Work -- 3 Causal Discovery Based on Genetic Algorithm -- 3.1 Data Pre-processing -- 3.2 Causal Relation Pre-discovering -- 3.3 Causal Graph Pruning -- 4 Experiments -- 4.1 Research Questions -- 4.2 Experiment Setting -- 4.3 Results and Analysis -- 5 Conclusion. , References -- Stochastic and Dual Adversarial GAN-Boosted Zero-Shot Knowledge Graph -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Background -- 3.2 Motivation -- 3.3 Framework of SDA -- 4 Experiments -- 4.1 Datasets Description -- 4.2 Baselines and Implementation Details -- 4.3 Result -- 4.4 Ablation Study -- 4.5 Influence of Word Embedding Method -- 5 Conclusions -- References -- Machine Learning -- LS-YOLO: Lightweight SAR Ship Targets Detection Based on Improved YOLOv5 -- 1 Introduction -- 2 Related Work -- 2.1 YOLOv5 Algorithm -- 2.2 CSP Module -- 3 The Proposed Method -- 3.1 LS-YOLO Network Structure -- 4 Experiment and Results -- 4.1 Experimental Configurations and Dataset -- 4.2 Evaluation Indicators -- 4.3 Experimental Results and Analysis -- 5 Conclusions -- References -- Dictionary Learning-Based Reinforcement Learning with Non-convex Sparsity Regularizer -- 1 Introduction -- 2 Related Work -- 3 Dictionary Learning-Based Reinforcement Learning with Non-convex Sparsity Regularizer -- 3.1 Problem Formulation -- 3.2 Optimization and Algorithm -- 4 Experiments and Discussions -- 4.1 Experiment Details -- 4.2 Parameter Selection -- 4.3 Performances Comparison -- 5 Conclusion -- References -- Deep Twin Support Vector Networks -- 1 Introduction -- 2 Related Work -- 3 Deep Twin Support Vector Networks -- 3.1 DTSVN for Binary Classification -- 3.2 Multiclass Deep Twin Support Vector Networks -- 3.3 Algorithm -- 3.4 Comparision with Shallow TSVM and Traditional DNN -- 4 Numerical Experiments -- 4.1 Experiments on Benchmark Datasets -- 4.2 Discussion on Parameter C -- 5 Conclusion -- References -- Region-Based Dense Adversarial Generation for Medical Image Segmentation -- 1 Introduction -- 2 Methods -- 2.1 Adversarial Examples -- 2.2 Target Adversary Generation -- 2.3 Region-Based Dense Adversary Generation -- 3 RESULT. , 3.1 Materials and Configurations -- 3.2 Evaluation Metrics -- 3.3 Results on DRIVE and CELL Datasets -- 3.4 The Adversarial Examples for Data Augmentation -- 4 Conclusion -- References -- Dynamic Clustering Federated Learning for Non-IID Data -- 1 Introduction -- 2 Related Work -- 3 Problem Definition -- 4 DCFL Framework -- 4.1 Client Design -- 4.2 Server Design -- 5 Experiments -- 5.1 Experimental Datasets -- 5.2 Experimental Settings -- 5.3 Experimental Results -- 6 Conclusion -- References -- Dynamic Network Embedding by Using Sparse Deep Autoencoder -- 1 Introduction -- 2 Definition and Problem Formulation -- 2.1 Definition -- 2.2 Problem Formulation -- 3 Our Algorithm: SPDNE -- 4 Experimental Results -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 5 Conclusion -- References -- Deep Graph Convolutional Networks Based on Contrastive Learning: Alleviating Over-smoothing Phenomenon -- 1 Introduction -- 2 Related Work -- 2.1 GCNs -- 2.2 Over-smoothing -- 2.3 Graph Contrastive Learning -- 3 Method -- 3.1 Contrast Structure and Data Augmentation -- 3.2 Contrastive Loss -- 3.3 For Node Classification Tasks on GCN -- 4 Experiments -- 4.1 Experimental Details -- 4.2 Pretraining Shallow GCN -- 4.3 Node Classification Results -- 5 Conclusion -- References -- Clustering-based Curriculum Construction for Sample-Balanced Federated Learning -- 1 Introduction -- 2 Related Work -- 2.1 Curriculum Learning -- 2.2 Federated Learning -- 3 Problem Formulation -- 4 Federation Curriculum Learning -- 4.1 Curriculum Generation (CG) Module -- 4.2 Curriculum Training (CT) Module -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Performance Comparison -- 5.3 Ablation Study -- 5.4 Case Study -- 6 Conclusion -- References -- A Novel Nonlinear Dictionary Learning Algorithm Based on Nonlinear-KSVD and Nonlinear-MOD -- 1 Introduction -- 2 Model and Formulation. , 3 Algorithm -- 3.1 Nonlinear Sparse Coding Based on NL-OMP -- 3.2 Nonlinear Dictionary Update -- 4 Numerical Experiments -- 4.1 Experimental Settings -- 4.2 Evaluation Indicators -- 4.3 Experimental Results -- 5 Conclusions and Discussions -- References -- Tooth Defect Segmentation in 3D Mesh Scans Using Deep Learning -- 1 Introduction -- 2 Related Work -- 2.1 3D Shape Segmentation -- 2.2 3D Teeth-related Tasks -- 3 Method -- 3.1 Data Pre-processing -- 3.2 Model Architecture -- 3.3 Loss -- 4 Experiment -- 4.1 Dataset and Experimental Setup -- 4.2 The Overall Performance -- 4.3 Ablation Studies -- 4.4 Visualization -- 5 Conclusion -- References -- Multi-agent Systems -- Crowd-Oriented Behavior Simulation:Reinforcement Learning Framework Embedded with Emotion Model -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Pedestrian Simulation Framework -- 3.2 Decision Realization Based on Emotion Model -- 3.3 Behavior Realization Based on ICM and PPO Algorithm -- 4 Experiments -- 4.1 Introduction to The Experimental System -- 4.2 Behavior Realization Comparative Experiment -- 4.3 A Variety of Emotional Simulation Experiments -- 5 Conclusion -- References -- Deep Skill Chaining with Diversity for Multi-agent Systems* -- 1 Introduction -- 2 Related Works -- 3 MARL with Skill Discovery -- 3.1 How Agents Learn their Policies -- 3.2 Option Framework -- 3.3 Problem Formulation -- 4 Methodology -- 4.1 Option Learning in MAS -- 4.2 Skill Chaining for MARL -- 4.3 Mutual Information for Space Exploration -- 5 Experimental Evaluations -- 5.1 SMAC Environment Setup -- 5.2 Mutual Information Evaluation -- 5.3 Performance Evaluation -- 6 Conclusions -- References -- Natural Language Processing -- Story Generation Based on Multi-granularity Constraints -- 1 Introduction -- 2 Related Works -- 2.1 Generation Framework -- 2.2 Controllable Story Generation. , 3 Methodology -- 3.1 Task Definition and Model Overview -- 3.2 Token-Level Constraint -- 3.3 Sentence-Level Constraint -- 4 Experimental Setup -- 4.1 Baselines -- 4.2 Evaluation Metrics -- 5 Results and Discussions -- 5.1 Automatic Evaluation and Human Evaluation -- 5.2 Case Study -- 6 Conclusion -- References -- Chinese Word Sense Embedding with SememeWSD and Synonym Set -- 1 Introduction -- 2 Related Work -- 2.1 Word Embedding -- 2.2 Word Sense Disambiguation and Word Sense Embedding -- 3 Methodology -- 3.1 OpenHowNet and SememeWSD -- 3.2 SWSDS Model -- 4 Experiment -- 4.1 SWSDS Experiment -- 4.2 Effectiveness Evaluation of SWSDS Model -- 5 Conclusion -- References -- Nested Named Entity Recognition from Medical Texts: An Adaptive Shared Network Architecture with Attentive CRF -- 1 Introduction -- 2 Related Work -- 2.1 Chinese Medical NER -- 2.2 Nested NER -- 2.3 Pre-trained Model -- 3 Methodology -- 3.1 Adaptive Shared Pre-trained Model -- 3.2 Attentive Conditional Random Fields -- 4 Experiments -- 4.1 Dataset -- 4.2 Experimental Setup -- 4.3 Results and Comparisons -- 4.4 Ablation Studies -- 5 Conclusion -- References -- CycleResume: A Cycle Learning Framework with Hybrid Attention for Fine-Grained Talent-Job Fit -- 1 Introduction -- 2 Framework Design -- 2.1 Problem Formulation -- 2.2 Architecture Overview -- 2.3 Feature Extraction -- 2.4 Fine-Grained Resume Representation Learning -- 2.5 Multi-scale Job-Post Representation Learning -- 2.6 Attention Based Resume-Job Fit Prediction -- 2.7 Training Methodology -- 3 Performance Evaluation -- 3.1 Dataset Description -- 3.2 Evaluation Metric -- 3.3 Experiment Setting -- 3.4 Evaluation Result -- 4 Conclusion and Future Work -- References -- Detecting Alzheimer's Disease Based on Acoustic Features Extracted from Pre-trained Models -- 1 Introduction -- 2 Methods. , 2.1 Extracting Bottleneck Features and Wav2vec 2.0 Representations from Pre-trained Models.

Anmerkung: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Contents - Part III -- Computer Vision -- Cross-Camera Deep Colorization -- 1 Introduction -- 2 Related Work -- 2.1 Automatic Image Colorization -- 2.2 Reference-based Image Colorization -- 2.3 Flow-based or Non-rigid Correspondences -- 3 Approach -- 3.1 Cross-camera Alignment Module -- 3.2 Hierarchical Fusion Module -- 3.3 Loss Function -- 4 Experiments -- 4.1 Dataset -- 4.2 Comparison to State-of-the-Art Methods -- 4.3 Ablation Study -- 5 Conclusion -- References -- Attentive Cascaded Pyramid Network for Online Video Stabilization -- 1 Introduction -- 2 Related Work -- 2.1 Traditional Offline 2D Video Stabilization -- 2.2 CNN Based Video Stabilization -- 3 Methods -- 3.1 RGB and Flow Feature Encoding -- 3.2 Flow-guided Quiescent Attention Module -- 3.3 Cascaded Pyramid Prediction Module -- 3.4 Training Objectives -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Quantitative Evaluation -- 4.3 Qualitative Evaluation -- 4.4 Ablation Study -- 4.5 User Study -- 5 Conclusions -- References -- Amodal Layout Completion in Complex Outdoor Scenes -- 1 Introduction -- 2 Related Work -- 2.1 Amodal Perception -- 2.2 Synthesize Image from Layout -- 3 Pre-experiments -- 3.1 Data Augmentation -- 3.2 Experiments and Evaluation -- 4 Methodology -- 4.1 Divide-and-Conquer Strategy -- 4.2 ALCN Mainframe -- 4.3 New Indicators -- 5 Experiments -- 5.1 Datasets and Evaluation Metrics -- 5.2 Experiments Results on Amodal Layout Completion -- 5.3 Experiments Results on Layout-to-Image Generation -- 5.4 Ablation Study -- 6 Conclusion -- References -- Exploring Hierarchical Prototypes for Few-Shot Segmentation -- 1 Introduction -- 2 Related Work -- 2.1 Few-shot Learning -- 2.2 Few-shot Segmentation -- 3 Method -- 3.1 Overview -- 3.2 Hierarchical Prototypes -- 3.3 Prototype Attention Module. , 4 Experiments -- 4.1 Experimental Settings -- 4.2 Performance Comparison -- 4.3 Ablation Study -- 5 Conclusion -- References -- BSAM: Bidirectional Scene-Aware Mixup for Unsupervised Domain Adaptation in Semantic Segmentation -- 1 Introduction -- 2 Methods -- 2.1 Preliminaries -- 2.2 Stylized Source Domain -- 2.3 Bidirectional Scene-Aware Mixup -- 2.4 Self-training Under Mean-Teacher Framework -- 3 Experiments -- 3.1 Implementation Details -- 3.2 Comparison with State-of-the-Art Methods -- 3.3 Parameter Analysis and Ablation Study -- 4 Conclusion -- References -- Triple GNN: A Pedestrian-Scene-Object Joint Model for Pedestrian Trajectory Prediction -- 1 Introduction -- 2 The Proposed Pedestrian-Scene-Object Joint Model for Pedestrian Trajectory Prediction -- 2.1 Problem Statements and the Framework of Our Work -- 2.2 Triple Feature Extraction -- 2.3 S-GNN with Two-stage Scheme -- 2.4 T-CNN with Dilated Convolution -- 3 Experiments, Results and Discussions -- 3.1 Experimental Settings -- 3.2 Overall Results -- 3.3 Ablation Experiments -- 3.4 Qualitative Evaluation -- 4 Conclusions -- References -- Cross-domain Trajectory Prediction with CTP-Net -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Problem Formulation -- 3.2 Cross-domain Trajectory Prediction Network -- 4 Experiments -- 4.1 Datasets and Evaluation Metrics -- 4.2 Experimental Setup -- 4.3 Implementation Details -- 4.4 Results -- 4.5 Ablation and Visulazation -- 5 Conclusion -- References -- Spatial-Aware GAN for Instance-Guided Cross-Spectral Face Hallucination -- 1 Introduction -- 2 Method -- 2.1 Spatial-aware Instance-guided Cross-spectral Face Hallucination -- 2.2 Fine-grained Aligned Spatially Adaptive Normalization -- 2.3 Training Objective -- 3 Experiments -- 3.1 Quantitative Evaluations -- 3.2 Qualitative Evaluations -- 3.3 Ablation Studies -- 4 Conclusion -- References. , Lightweight Image Compression Based on Deep Learning -- 1 Introduction -- 2 The Proposed Methods -- 2.1 Dynamic Concatenated Convolution (DCC) -- 2.2 Depthwise Separable Residual Block (DSRB) -- 3 Experiments -- 3.1 Implementation Details -- 3.2 Lightweight Ability Evaluation -- 3.3 Generalization Ability Evaluation -- 3.4 Ablation Study -- 4 Conclusion -- References -- DGMLP: Deformable Gating MLP Sharing for Multi-Task Learning -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Overview -- 3.2 Feature Extractor -- 3.3 DGMLP Method -- 3.4 Loss Function -- 4 Experiments -- 4.1 Comparisons with State-of-the-art Models -- 4.2 Ablation Study -- 4.3 Visualization -- 5 Conclusion -- References -- Monocular 3D Face Reconstruction with Joint 2D and 3D Constraints -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 3D Morphable Model -- 3.2 Joint 2D and 3D Optimization -- 4 Experimental Results -- 4.1 Datasets and Metrics -- 4.2 Ablation Study -- 4.3 Comparison -- 5 Conclusion and Discussion -- References -- Scene Text Recognition with Single-Point Decoding Network -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Rectifier -- 3.2 Encoder -- 3.3 Decoder -- 3.4 Loss Function -- 4 Experiments -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Comparisons with State-of-the-Arts -- 4.4 Ablation Study -- 4.5 Visual Illustrations -- 5 Conclusion -- References -- Unsupervised Domain Adaptation for Semantic Segmentation with Global and Local Consistency -- 1 Introduction -- 2 Related Work -- 2.1 Semantic Segmentation -- 2.2 Unsupervised Domain Adaptation -- 3 Methods -- 3.1 Global Consistency -- 3.2 Local Consistency -- 3.3 Overall Training Loss -- 4 Experiments -- 4.1 Datasets -- 4.2 Implementation Details -- 4.3 Results -- 5 Conclusion -- References -- Research on Multi-temporal Cloud Removal Using D-S Evidence Theory and Cloud Segmentation Model. , 1 Introduction -- 2 Related Work -- 2.1 Cloud Removal Methods -- 2.2 Cloud Detection Methods -- 3 Methods -- 3.1 Cloud-net -- 3.2 Color Prior Knowledge -- 3.3 D-S Evidence Theory -- 3.4 Evidence Fusion Method -- 4 Experiment -- 4.1 Training Cloud-net -- 4.2 Experiments with Color Prior Knowledge -- 4.3 Multi-temporal Remote Sensing Cloud Removal Experiments -- 4.4 Ablation Experiment -- 4.5 Comparison Against Other Cloud Removal Methods -- 5 Conclusion -- References -- SASD: A Shape-Aware Saliency Object Detection Approach for RGB-D Images -- 1 Introduction -- 2 Related Work -- 3 The Proposed SASD Approach -- 3.1 Initial Saliency Map Calculation -- 3.2 Enhanced Saliency Map Calculation -- 3.3 Irregular Shape Display -- 4 Experiments and Discussion -- 5 Conclusion -- References -- Dual Windows Are Significant: Learning from Mediastinal Window and Focusing on Lung Window -- 1 Introduction -- 2 Related Works -- 2.1 Computer-Aid Diagnosis Systems for Pneumonia -- 2.2 Attention Mechanisms -- 3 Methods -- 3.1 Dual Window Network -- 3.2 Lung Window Attention Block -- 3.3 Overall Loss -- 4 Experiments -- 4.1 Evaluation Dataset and Experimental Settings -- 4.2 Experimental Analyse -- 5 Discussion -- 6 Conclusions -- References -- CDNeRF: A Multi-modal Feature Guided Neural Radiance Fields -- 1 Introduction -- 2 Related Work -- 2.1 Neural Radiance Field with Generality -- 2.2 Depth Prior to NeRF -- 3 Methods -- 3.1 Multi-modal Feature Extraction -- 3.2 Radiance Field Prediction and Volumetric Rendering -- 3.3 Optimization Functions -- 4 Experiments -- 4.1 Datasets and Evaluation -- 4.2 Implementation Details -- 4.3 Results -- 4.4 Ablation and Analysis -- 5 Conclusion -- References -- MHPro: Multi-hypothesis Probabilistic Modeling for Human Mesh Recovery -- 1 Introduction -- 2 Related Work -- 2.1 Human Mesh Recovery from Monocular Images. , 2.2 Multi-hypothesis Methods -- 2.3 Transformer in Computer Vision -- 3 Method -- 3.1 Preliminary -- 3.2 Probabilistic Modeling -- 3.3 Intra-hypothesis Refinement -- 3.4 Inter-hypothesis Communication -- 3.5 Loss Function -- 4 Experimental Results -- 4.1 Datasets -- 4.2 Comparison -- 4.3 Ablation Study -- 5 Conclusion -- References -- Image Sampling for Machine Vision -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Motivation -- 3.2 Implementation -- 3.3 Visualization -- 3.4 Cost Assessment -- 4 Experiments -- 4.1 Object Detection -- 4.2 Image Classification -- 4.3 Ablation Experiments -- 4.4 Effect Visualization -- 5 Conclusion -- References -- SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning -- 1 Introduction -- 2 Related Work -- 2.1 Filter Channel Pruning -- 2.2 Filter Weight Pruning -- 2.3 Hybrid Filter Pruning -- 3 Proposed Method -- 3.1 Filter Skeleton (FS) for Kernel Size Reduction -- 3.2 Filter Mask (FM) for Filter Number Reduction -- 3.3 Training and Inference -- 4 Experiments -- 4.1 ResNet56 on CIFAR-10 -- 4.2 ResNet18 on ImageNet -- 4.3 U-Net for Image Denoising -- 5 Conclusions -- References -- H-ViT: Hybrid Vision Transformer for Multi-modal Vehicle Re-identification -- 1 Introduction -- 2 Related Work -- 2.1 Single-Modal Re-identification -- 2.2 Multi-modal Re-identification -- 2.3 Transformer in Re-identification Task -- 3 Method -- 3.1 Vision Transformer Branches and Loss Function -- 3.2 Modal-specific Controller -- 3.3 Modal Information Embedding -- 4 Experiments and Analysis -- 4.1 Datasets -- 4.2 Implementation -- 4.3 Comparison with State-of-the-Art -- 4.4 Analysis -- 5 Conclusion -- References -- A Coarse-to-Fine Convolutional Neural Network for Light Field Angular Super-Resolution -- 1 Introduction -- 2 Proposed Method -- 2.1 Coarse-grained View Synthesis Sub-network. , 2.2 Fine-grained View Refinement Sub-network.

Anmerkung: Intro -- Preface -- Organization -- Contents - Part II -- Contents - Part I -- Explainability, Understandability, and Verifiability of AI -- Reducing Adversarial Examples Through Boundary Methods -- 1 Introduction -- 2 Related Works -- 3 Boundary Margin -- 3.1 Large Margin Methods -- 3.2 Informal Definition of Non-robust Features -- 3.3 Experiments on MNIST and CIFAR10 -- 4 Boundary Thickness -- 4.1 Comparison of Boundary Thickness and Margin -- 4.2 Mixup and Boundary Thickness -- 5 Boundary Methods and Feature Space -- 6 Conclusions -- References -- Explainable AI for Classification Using Probabilistic Logic Inference -- 1 Introduction -- 2 Training as Knowledge Base Construction -- 3 Querying as Probabilistic Inference -- 4 Explanations -- 5 Performance Analysis -- 6 Related Work -- 7 Conclusion -- References -- A Consistency Regularization for Certified Robust Neural Networks -- 1 Introduction -- 2 Related Works -- 2.1 Empirical Adversarial Defense -- 2.2 Certified Adversarial Defense -- 3 Methods -- 3.1 Preliminaries -- 3.2 Misclassification Aware Training -- 3.3 Misclassification Aware Adversarial Regularization -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Sensitivity of Regularization Parameter -- 4.3 the Effectiveness of MAAR -- 4.4 Certification Under Different Perturbations -- 4.5 Comparison with Prior Work on Different Datasets -- 5 Conclusion -- References -- Fooling Neural Network Interpretations: Adversarial Noise to Attack Images -- 1 Introduction -- 2 Related Work -- 2.1 Local-level Interpretation Methods -- 2.2 Fooling Network Interpretation -- 3 Methods -- 3.1 Fooling Interpretation with the Noise -- 3.2 Fooling Interpretation with the Universal Noise -- 3.3 Fooling Interpretation with the Image Patches -- 3.4 Constraining the Noise -- 4 Experiments -- 4.1 Evaluation -- 4.2 Single-target Attack of Interpretation. , 4.3 Multi-target Attack of Interpretation -- 4.4 Transfer to Different Interpretation Methods -- 4.5 Fooling Interpretation with the Universal Noise -- 4.6 Fooling Interpretation with the Image Patches -- 5 Conclusion -- References -- Machine Learning -- BPN: Bidirectional Path Network for Instance Segmentation -- 1 Introduction -- 2 Related Work -- 2.1 Proposal-Based and Proposal-Free Approaches -- 2.2 Integrating Multi-level Knowledge -- 3 BPN -- 3.1 Multi-level Feature Fusion -- 3.2 Residual Dense Connection -- 3.3 Bidirectional Paths Network -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Experiments on COCO -- 4.3 Ablation Study -- 5 Conclusion -- References -- Claw U-Net: A UNet Variant Network with Deep Feature Concatenation for Scleral Blood Vessel Segmentation -- 1 Introduction -- 2 Claw UNet -- 2.1 Claw UNet Architecture -- 2.2 Feature Learning and Fusion -- 2.3 Comparison with UNet and UNet++ -- 3 Experiments and Results -- 3.1 Experimental Protocol -- 3.2 Comparison with Other UNet-Based Models -- 3.3 Ablation Experiments -- 3.4 Robustness Experiments -- 4 Conclusion -- References -- Attribute and Identity Are Equally Important: Person Re-identification with More Powerful Pedestrian Attributes -- 1 Introduction -- 2 Related Work -- 3 The Proposed Method -- 3.1 Pedestrian Attribute Recognition -- 3.2 Joint Recognition Model -- 3.3 Loss Function -- 4 Experimental Result -- 4.1 Pedestrian Attribute Recognition -- 4.2 Person Re-identification -- 5 Conclusions and Future Work -- References -- Disentangled Variational Information Bottleneck for Multiview Representation Learning -- 1 Introduction -- 2 Preliminaries and Existing Works -- 3 Disentangled Variational Information Bottleneck -- 3.1 Information Bottleneck for the Shared Representation -- 3.2 Information Bottleneck for the Private Representation -- 3.3 Variational Bounds. , 3.4 Optimization -- 4 Experiments -- 4.1 Evaluation of Information Disentanglement on MNIST -- 4.2 Evaluation Using Corrupted Samples on ImageNet -- 4.3 Robustness to Image Corruption Levels -- 5 Discussion -- References -- Real-Time Collision Warning and Status Classification Based Camera and Millimeter Wave-Radar Fusion -- 1 Introduction -- 2 Method -- 2.1 FMCW Radar Signal Model -- 2.2 Radar Network -- 2.3 Radar and Camera Fusion -- 2.4 Status Classification and Dataset -- 3 Experimental Results and Analysis -- 3.1 Validation of Basic Functions -- 3.2 Results in Real-World -- 3.3 Qualitative Analysis -- 4 Conclusion -- References -- AD-DARTS: Adaptive Dropout for Differentiable Architecture Search -- 1 Introduction -- 2 Existing Problems of DARTS -- 2.1 Differentiable Architecture Search -- 2.2 Performance Collapse Caused by Parameter-Free Operations -- 2.3 Unfair and Inadequate Training Scheme -- 3 The Adaptive Dropout Methodology -- 3.1 Motivation -- 3.2 Operation-Level Adaptive Dropout -- 4 Experiments and Results -- 4.1 Implementation Details and Performance Comparation -- 4.2 Influence of Hyper-parameter -- 4.3 Search Stability Study -- 5 Conclusion -- References -- An Improved DDPG Algorithm with Barrier Function for Lane-Change Decision-Making of Intelligent Vehicles -- 1 Introduction -- 2 Background -- 2.1 A Safety Distance in Lane Change Decision -- 2.2 Autonomous Driving Based on DDPG Algorithm -- 3 DDPG Algorithm with Barrier Function -- 3.1 The Barrier Function for Safe Lane Change -- 3.2 Constructing Barrier Function by Interior Point Method -- 3.3 Algorithm Process of DDPG-BF -- 4 Experiments -- 4.1 Experimental Preparations -- 4.2 Comparative Analysis of Experimental Data -- 5 Conclusion -- References -- Self-organized Hawkes Processes -- 1 Introduction -- 2 Proposed Model. , 2.1 Continuous-Time Recommendation Based on Hawkes Processes -- 2.2 Self-organized Hawkes Processes -- 3 Learning Algorithm -- 3.1 A Reward-Augmented Bandit Algorithm -- 3.2 Merging Learned Hawkes Processes -- 4 Related Work -- 5 Experiments -- 6 Conclusion -- References -- Causal Inference with Heterogeneous Confounding Data: A Penalty Approach -- 1 Introduction -- 2 Related Work -- 3 Heterogeneous subGroup Balance Adaptive Method -- 3.1 Problem Formulation -- 3.2 Heterogeneous subGroup Balance Adaptive Method -- 3.3 Theoretical Analysis -- 3.4 Choice of Hyperparameters -- 4 Experiments -- 4.1 Datasets and Settings -- 4.2 Results and Analysis -- 5 Conclusion -- References -- Optimizing Federated Learning on Non-IID Data Using Local Shapley Value -- 1 Introduction -- 2 Related Work -- 2.1 Federated Learning Settings -- 2.2 Model Optimization Algorithm -- 3 Preliminary -- 3.1 Federated Learning -- 3.2 Shapley Value -- 4 Proposed Method -- 4.1 Problem Formulation -- 4.2 Local Federated Shapley Value -- 4.3 Dynamical Weights Update -- 4.4 Algorithm -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Experimental Results -- 6 Conclusion -- References -- Boosting Few-Shot Learning with Task-Adaptive Multi-level Mixed Supervision -- 1 Introduction -- 2 Proposed Method -- 2.1 Problem Definition -- 2.2 Task-Adaptive FSL with Multi-level Mixed Supervision -- 2.3 Multi-level Mixed Supervision with Unbalanced Prior -- 2.4 FSL Model Solution -- 3 Experiments -- 3.1 Setup -- 3.2 Comparison with SOTA Works -- 3.3 Ablation Study -- 4 Conclusion -- References -- Learning Bilevel Sparse Regularized Neural Network -- 1 Introduction -- 2 Proposed Approaches -- 2.1 A Strong Connection Between Regularization and Activation Function -- 2.2 Learnable Bilevel Sparse Regularizer -- 2.3 Learning Bilevel Sparse Regularized Neural Network (BSRL) -- 2.4 Framework of BSRL. , 3 Experiments -- 3.1 Baselines -- 3.2 Datasets -- 3.3 Experimental Results and Analysis -- 4 Conclusion -- References -- Natural Language Processing -- DGA-Net: Dynamic Gaussian Attention Network for Sentence Semantic Matching -- 1 Introduction -- 2 Related Work -- 3 Problem Statement and Model Structure -- 3.1 Problem Statement -- 3.2 Dynamic Gaussian Attention Network -- 4 Experiment -- 4.1 Experimental Setup -- 4.2 Experiment Results -- 4.3 Ablation Performance -- 4.4 Sensitivity of Parameters -- 5 Conclusion and Future Work -- References -- Disentangled Contrastive Learning for Learning Robust Textual Representations -- 1 Introduction -- 2 Related Work -- 3 Preliminaries on Learning Robust Textual Representations -- 4 Disentangled Contrastive Learning -- 4.1 Feature Alignment with Momentum Representation Consistency -- 4.2 Feature Uniformity with Power Normalization -- 4.3 Implementation Details -- 5 Experiment -- 5.1 Datasets and Setting -- 5.2 Results and Analysis -- 5.3 Discussion -- 6 Conclusion -- References -- History-Aware Expansion and Fuzzy for Query Reformulation -- 1 Introduction -- 2 Related Work -- 3 Models -- 3.1 History-Aware Term Weight (HaTwei) -- 4 Experiment -- 5 Conclusion -- References -- Stance Detection with Knowledge Enhanced BERT -- 1 Introduction -- 2 Method -- 2.1 Task Definition -- 2.2 Knowledge Integration -- 2.3 Stance Detection -- 3 Experiment -- 3.1 Dataset -- 3.2 Experimental Settings -- 3.3 Experimental Results -- 4 Related Work -- 4.1 Stance Detection -- 4.2 Pre-trained Language Model -- 5 Conclusion -- References -- Towards a Two-Stage Method for Answer Selection and Summarization in Buddhism Community Question Answering -- 1 Introduction -- 2 Method -- 2.1 Problem Definition -- 2.2 Keywords-BERT -- 2.3 Keywords Collection -- 2.4 Training an Answer Selection Model -- 2.5 Extractive Summarization. , 3 Dataset and Experimental Setting.

Anmerkung: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Applications of AI -- Comparative Sharpness Evaluation for Mobile Phone Photos -- 1 Introduction -- 2 The Comparative Evaluation Algorithm -- 2.1 Image Pre-processing -- 2.2 The Comparative Sharpness Evaluation Model -- 2.3 Ranking Method -- 3 Experimental Results -- 3.1 Implementation Details -- 3.2 Performance Evaluation -- 3.3 Ablation Study -- 4 Conclusion -- References -- DiffGNN: Capturing Different Behaviors in Multiplex Heterogeneous Networks for Recommendation -- 1 Introduction -- 2 Related Work -- 2.1 Network Embedding -- 2.2 Heterogeneous Network Embedding -- 2.3 GNN Models in Recommender Systems -- 3 Methodology -- 3.1 Metapath Aware Aggregation -- 3.2 Relation-Specific Attention -- 4 Experiments -- 4.1 Baselines and Experimental Settings -- 4.2 Experimental Results and Analysis -- 5 Conclusion -- References -- Graph-Based Exercise- and Knowledge-Aware Learning Network for Student Performance Prediction -- 1 Introduction -- 2 Related Work -- 2.1 Educational Psychology -- 2.2 Collaborative Filtering in Recommender Systems -- 2.3 Collaborative Filtering in ITS -- 3 The Proposed Model -- 3.1 Problem Formulation -- 3.2 Overall Structure -- 3.3 Modeling High-Order Collaborative Information -- 3.4 Modeling Information of Knowledge Concepts -- 3.5 Performance Prediction -- 4 Experiments -- 4.1 Dataset Description -- 4.2 Experimental Settings -- 4.3 Experimental Results -- 4.4 Detailed Model Analyses -- 5 Conclusions -- References -- Increasing Oversampling Diversity for Long-Tailed Visual Recognition -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Problem Setup -- 3.2 mixSMOTE -- 3.3 Gradient Re-weighting Module -- 4 Experiments -- 4.1 Results on Imbalanced CIFAR -- 4.2 Results on ImageNet-LT -- 4.3 Ablation Study -- 5 Conclusion -- References. , Odds Estimating with Opponent Hand Belief for Texas Hold'em Poker Agents -- 1 Introduction -- 2 Related Work -- 3 Methods Considering Hand Belief -- 3.1 Expected Win Rate Algorithm with Start Hand Range (EWR-SHR) -- 3.2 Expected Win Rate Algorithm with Fold Rate (EWR-FR) -- 3.3 Expected Win Rate Algorithm with Hand Distribution (EWR-HD) -- 4 Computation Experiments -- 5 Conclusion -- References -- Remote Sensing Image Recommendation Using Multi-attribute Embedding and Fusion Collaborative Filtering Network -- 1 Introduction -- 2 Related Works -- 3 Framework Overview -- 3.1 Image and User Semantic Information Extraction -- 3.2 Knowledge Graph Construction and Vector Representation -- 3.3 Multi-attribute Fusion-Based Collaborative Filtering Network -- 4 Experiments and Evaluation -- 4.1 Data and Experimental Settings -- 4.2 Experimental Results and Discussion -- 5 Conclusion -- References -- Object Goal Visual Navigation Using Semantic Spatial Relationships -- 1 Introduction -- 2 Related Work -- 3 Proposed Approach -- 3.1 Task Definition -- 3.2 Construction of Semantic Relation Graph -- 3.3 Joint Representation of Spatial Context Information -- 3.4 Navigation Driven by Spatial Semantic Relationships of Objects -- 4 Experiments -- 4.1 Datasets -- 4.2 Implementations and Evaluation Metircs -- 4.3 Comparison Models -- 4.4 Results -- 5 Conclusion -- References -- Classification of COVID-19 in CT Scans Using Image Smoothing and Improved Deep Residual Network -- 1 Introuduction and Related Work -- 2 Methods -- 2.1 Dataset -- 2.2 Data Pre-processing -- 2.3 The Proposed Architecture -- 3 Results -- 3.1 Experimental Configuration -- 3.2 Experimental Results and Analysis -- 4 Ablation Studies -- 4.1 Image Smoothing Contrast Results and Analysis -- 4.2 Improved Module Comparison Results and Analysis -- 5 Conclusion -- References. , Selected Sample Retraining Semi-supervised Learning Method for Aerial Scene Classification -- 1 Introduction -- 2 Methodology -- 2.1 Unlabeled Samples Labeling with Early Training Multi-Models -- 2.2 High Probability Sample Selection -- 2.3 Retraining -- 3 Experimental Results -- 3.1 Data Set Description -- 3.2 Implementation Details -- 3.3 Experimental Results and Analysis -- 4 Conclusion -- References -- Knowledge Powered Cooperative Semantic Fusion for Patent Classification -- 1 Introduction -- 2 Related Work -- 2.1 Patent Classification -- 2.2 Knowledge-Enhanced Short Text Classification -- 3 The Proposed Model KCSF -- 3.1 Knowledge Powered Semantic Augmentation -- 3.2 Mutual Attention Mechanism -- 3.3 Entity-Based Graph Convolutional Network -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experimental Results and Ablation Studies -- 4.3 Sensitivity Analysis on Neighborhood Graph Size -- 5 Conclusion -- References -- Diagnosis of Childhood Autism Using Multi-modal Functional Connectivity via Dynamic Hypergraph Learning -- 1 Introduction -- 2 Methods -- 2.1 Databases and Preprocessing -- 2.2 Feature Selection -- 2.3 Multi-modal Dynamic Hypergraph Learning for ASD Diagnosis -- 3 Experiments and Discussions -- 3.1 Experimental Settings -- 3.2 Experimental Results and Discussions -- 3.3 On Parameters -- 3.4 Visualization -- 4 Conclusion -- References -- CARNet: Automatic Cerebral Aneurysm Classification in Time-of-Flight MR Angiography by Leveraging Recurrent Neural Networks -- 1 Introduction -- 2 Methods -- 2.1 MIP Extracting -- 2.2 CGA Discrimination -- 3 Experiment and Setup -- 3.1 Dataset -- 3.2 Evaluation Metrics -- 3.3 Data Augmentation -- 3.4 CARNet Training -- 4 Results -- 5 Conclusion -- References -- White-Box Attacks on the CNN-Based Myoelectric Control System -- 1 Introduction -- 2 Methods -- 2.1 Date Collection. , 2.2 The Architecture of CNN Network -- 2.3 Attack Algorithm -- 2.4 Performance Evaluation -- 3 Results and Discussions -- 3.1 Non-target Attack on the CNN Network -- 3.2 Target Attack on the CNN Network -- References -- MMG-HCI: A Non-contact Non-intrusive Real-Time Intelligent Human-Computer Interaction System -- 1 Introduction -- 2 Related Works -- 2.1 Human Activity Recognition and Gesture Recognition -- 2.2 Millimeter-Wave Radar -- 2.3 Graph Neural Networks -- 3 System Workflow -- 3.1 Data Flow -- 3.2 Model -- 4 Data Collection and Processing -- 4.1 Radar Configuration -- 4.2 Data Collection -- 4.3 Data Processing -- 5 Experiment and Demonstration -- 6 Conclusions -- References -- DSGSR: Dynamic Semantic Generation and Similarity Reasoning for Image-Text Matching -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Cross-Modal Feature Representation -- 3.2 Enriched Regional Semantics -- 3.3 Dynamic Generation Module -- 3.4 Similarity Reasoning Module -- 4 Experiments -- 4.1 Datasets -- 4.2 Experimental Settings -- 4.3 Experimental Results -- 4.4 Ablation Studies -- 4.5 Qualitative Result -- 5 Conclusion -- References -- Phase Partition Based Virtual Metrology for Material Removal Rate Prediction in Chemical Mechanical Planarization Process -- 1 Introduction -- 2 Method -- 2.1 Phase Partition Based on WKM and PPCI -- 2.2 Phase Match -- 2.3 Feature Extraction and Feature Selection -- 2.4 Regression Model -- 3 Case Study -- 3.1 Description of the Dataset -- 3.2 Phase Partition and Phase Match -- 3.3 Feature Extraction and Feature Selection -- 3.4 Prediction Performance and Discussions -- 4 Conclusion -- References -- SAR Target Recognition Based on Model Transfer and Hinge Loss with Limited Data -- 1 Introduction -- 2 Method -- 2.1 Multi-class Hinge Loss for SAR-ATR -- 2.2 WGAN-HL-Convnet -- 3 Experiments and Results -- 3.1 Experimental Data Sets. , 3.2 Training Details -- 3.3 Experiment Results -- 4 Conclusion -- References -- Neighborhood Search Acceleration Based on Deep Reinforcement Learning for SSCFLP -- 1 Introduction -- 2 Related Work -- 2.1 Lagrangian Relaxation Based Methods -- 2.2 Meta Heuristics -- 2.3 Machine Learning Based Methods -- 3 Problem Definition -- 4 Proposed Approach -- 4.1 Graph Representation -- 4.2 Model -- 4.3 Neighborhood Operator -- 4.4 Training Procedure -- 5 Experiments -- 5.1 Data Generation and Algorithm Settings -- 5.2 Results and Analysis -- 6 Conclusion -- References -- GBCI: Adaptive Frequency Band Learning for Gender Recognition in Brain-Computer Interfaces -- 1 Introduction -- 2 Materials -- 2.1 Participants and Equipment -- 2.2 Experimental Paradigm and Procedure -- 2.3 EEG Data Preprocessing -- 3 Methodology -- 3.1 Channel Selection -- 3.2 Adaptive Variable Mode Decomposition -- 3.3 LSTM Network -- 4 Results and Discussion -- 4.1 Results Using Our AVMD-LSTM Method Based on Different Data -- 4.2 Channel Selection Based on Sample Entropy -- 4.3 Efficacy of Our Model Structure -- 5 Conclusion -- References -- Computer Vision -- Hybrid Domain Convolutional Neural Network for Memory Efficient Training -- 1 Introduction -- 2 Related Work -- 2.1 Memory Scheduling -- 2.2 Compact Representation of Feature Maps -- 2.3 Memory Efficient CNN Architectures -- 2.4 CNN in the Frequency Domain -- 2.5 Model Compression -- 3 The Proposed Method -- 3.1 Convolution -- 3.2 Activation -- 3.3 Maxpooling -- 4 Experiments -- 4.1 Results on CIFAR-10 -- 4.2 Results on ImageNet -- 5 Ablation Study -- 6 Conclusion -- References -- Brightening the Low-Light Images via a Dual Guided Network -- 1 Introduction -- 2 Methodology -- 2.1 Depth Guided Illumination Estimation -- 2.2 Attention Guided Reflectance Enhancement -- 2.3 Loss Function -- 3 Experiment -- 3.1 Experimental Details. , 3.2 Ablation Study.