Advanced Intelligent Computing Technology and Applications : 20th International Conference, ICIC 2024, Tianjin, China, August 5–8, 2024, Proceedings, Part VI / / edited by De-Shuang Huang, Zhanjun Si, Jiayang Guo

• Record Nr.: UNINA9910878992303321
• Pubbl/distr/stampa: Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024
• ISBN: 981-9755-97-2
• Edizione: [1st ed. 2024.]
• Descrizione fisica: 1 online resource (516 pages)
• Collana: Lecture Notes in Computer Science, , 1611-3349 ; ; 14867
• Disciplina: 006.3
• Soggetti: Computational intelligence; Computer networks; Machine learning; Application software; Computational Intelligence; Computer Communication Networks; Machine Learning; Computer and Information Systems Applications
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part VI -- Image Processing -- Dual-Stream Input Gabor Convolution Network for Building Change Detection in Remote Sensing Images -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Overall Framework -- 3.2 SCM Module -- 3.3 AFM Module -- 3.4 Loss Function -- 4 Experiment Results and Analysis -- 4.1 Datasets and Experimental Platform -- 4.2 Evaluation Metric -- 4.3 The Influence of Different Parameters in Gabor Convolution -- 4.4 Comparative Experiment -- 4.5 Ablation Experiment -- 5 Conclusion -- References -- Contextual Feature Modulation Network for Efficient Super-Resolution -- 1 Introduction -- 2 Related Work -- 2.1 Deep Learning-Based Image Super-Resolution -- 2.2 Efficient Image Super-Resolution -- 3 Proposed Method -- 3.1 Network Architecture -- 3.2 Multi-scale Feature Spatial Modulation -- 3.3 Channel Attention Fusion ; Module -- 3.4 Feature Fusion Module -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Comparison to Other Methods -- 4.3 Ablation -- 5 Conclusion -- References -- Fine-Grained Image Editing Using ControlNet: Expanding Possibilities in Visual Manipulation -- 1 Introduction -- 2 Related Work -- 2.1 Image Editing -- 2.2 Image Editing -- 3 Method -- 3.1 Partial Mask -- 3.2 Spatial Features Injection -- 3.3 Classifier-Guidance-Based Editing Design -- 4 Experiment -- 4.1 Implementation Details -- 4.2 Metrics -- 4.3 Ablation Study -- 4.4 Qualitative Evaluation -- 4.5 Quantitative Evaluation -- 5 Conclusion -- References -- MDIINet: A Few-Shot Semantic Segmentation Network by Exploiting Multi-dimensional Information Interaction -- 1 Introduction -- 2 Problem Setup -- 3 Proposed Approach -- 3.1 Inter-class Feature Fusion Module -- 3.2 High-Level Feature Extraction Module -- 3.3 Feature Fusion and Decoded Output -- 3.4 Hybrid Loss -- 4 Experiments -- 4.1 Experimental Setting.; 4.2 Results and Analysis -- 4.3 Ablation Study -- 5 Conclusion -- References -- A Large Model Assisted Remote Sensing Image Scene Understanding Algorithm Based on Object Detection -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 3.1 Network Structure of Large Model Assisted Visual Scene Understanding Algorithm -- 3.2 Prompt Engineering Based on Large Language Modelg -- 4 Experiments -- 4.1 Scene Description and Visualization Analysis of QA -- 4.2 Design of Visual Scene Understanding System -- 5 Conclusion -- References -- PCLMix: Weakly Supervised Medical Image Segmentation via Pixel-Level Contrastive Learning and Dynamic Mix Augmentation -- 1 Introduction -- 2 Methodology -- 2.1 Overview -- 2.2 Dynamic Mix Augmentation from Heterogeneous Views -- 2.3 Uncertainty-Guided Pixel-Level Contrastive Learning -- 2.4 Regularization of Supervision via Dual Consistency -- 3 Experiments -- 3.1 Experimental Setup -- 3.2 Quantitative Comparison -- 3.3 Ablation Study -- 3.4 Visualization Analysis -- 4 Conclusions -- References -- Few-Shot Domain Adaptation via Prompt-Guided Multi-prototype Alignment Network -- 1 Introduce -- 2 Relate Work -- 3 Method -- 3.1 Prompt-Based Prototype Alignment Network -- 3.2 Domain-Specific Feature Mapping Network -- 3.3 Design of Multi-text-Guided Soft Prompts -- 4 Experiments -- 4.1 Experiment Setting -- 4.2 Implementation Details. -- 4.3 Comparison with State-Of-The-Art DA Methods -- 4.4 Ablation Study and Analyse -- 5 Conclusion -- References -- Controllable Rain Image Generation: Balance Between Diversity and Controllability -- 1 Introduction -- 2 The Proposed Method -- 2.1 Generative Model -- 2.2 Training Strategy -- 3 Experimental Results -- 3.1 Rain Generation Experiments -- 3.2 Disentanglement Experiments -- 3.3 Rain Removal Experiments -- 4 Conclusion and Future Work -- References.; Unsupervised Domain Adaptation in Medical Image Segmentation via Fourier Feature Decoupling and Multi-teacher Distillation -- 1 Introduction -- 2 Related Work -- 2.1 Unsupervised Domain Adaptation -- 2.2 Multi-teacher Knowledge Distillation Models -- 3 Method Overview -- 3.1 Feature Decoupling Based on Fourier Transform -- 3.2 Multi-teacher Knowledge Distillation Module -- 3.3 Dynamic Weighting Adaptive Strategy -- 4 Experiments -- 4.1 Dataset and Evaluation Metrics -- 4.2 Validation of Different Models Adaptability in the Target Domain -- 4.3 Validation of the Effectiveness of Fourier Feature Decoupling Method -- 4.4 Performance Validation of Multi-teacher Knowledge Distillation Network -- 5 Conclusion -- References -- DeCoGAN: Photo Cartoonization Based on Deformation Consistency GAN -- 1 Introduction -- 2 Methodology -- 2.1 Network Architecture -- 2.2 Loss Function -- 3 Experiments -- 3.1 Dataset -- ; 3.2 Parameters -- 3.3 Qualitative Evaluation -- 3.4 Quantitative Evaluation -- 3.5 Ablation Study -- 4 Conclusion and Limitation -- References -- Self-supervised Siamese Networks with Squeeze-Excitation Attention for Ear Image Recognition -- 1 Introduction -- 2 Classical Convolutional Neural Network -- 3 Methods -- 3.1 Siamese Network -- 3.2 SE-SiamNet -- 4 Experimental Result -- 4.1 Dataset Description -- 4.2 Experimental Setup -- 4.3 Result Analysis -- 5 Conclusion -- References -- CtF: Mitigating Visual Confusion in Continual Learning Through a Coarse-To-Fine Screening -- 1 Introduction -- 2 Related Work -- 2.1 Continual Learning -- 2.2 Vision-Language Model -- 3 Proposed Method -- 3.1 Preliminary Analysis -- 3.2 Coarse-To-Fine Screening Framework -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Quantitative Evaluation -- 4.3 Ablation Study -- 4.4 Sensitivity Study -- 5 Conclusion -- References -- HDR Video Coding Based on Perceptual Optimization.; 1 Introduction -- 2 Perceptual Optimization Model -- 2.1 Perceptual Lossless Preprocessing Model -- 2.2 Visual Perceptual Saliency -- 2.3 CTU-Level Quantization Model -- 3 Results and Analysis -- 4 Conclusion -- References -- Infrared-Visible Light Image Fusion Method Based on Weighted Salience Detection and Visual Information Preservation -- 1 Introduction -- 2 Proposed Method -- 2.1 Two-Scale Image Decomposition Based on Average Filter -- 2.2 Weighted Visual Significance Feature Extraction -- 2.3 The Final Detail Layer and Visible Image Fusion Based on Grayscale Driven -- 3 Experiments and Results -- 3.1 Experimental Setup -- 3.2 Comparative Experiment -- 4 Conclusions -- References -- CAT-DG: A Cross-Attention-Based Domain Generalization Model for Medical Image Segmentation -- 1 Introduction -- 2 Related Work -- 2.1 Concepts Related to Domain Generalization -- 2.2 The FLLN-DG Model -- 2.3 Cross-Attention Mechanism -- 3 Cross-Attention-Based Segmentation Model for Domain Generalization -- 3.1 Model Architecture -- 3.2 Cross-Attention Module -- 3.3 Loss Function -- 4 Experiments and Results -- 4.1 Dataset and Parameter Settings -- 4.2 Performance Comparison of Different Models -- 4.3 Ablation Experiments -- 5 Conclusion -- References -- Superpixel-Based Dual-Neighborhood Contrastive Graph Autoencoder for Deep Subspace Clustering of Hyperspectral Image -- 1 Introduction -- 2 Proposed Methods -- 2.1 Construction of Dual-Neighborhood Graph -- 2.2 Superpixel Dual-Neighborhood Contrastive Graph Autoencoder -- 2.3 Contrastive Learning -- 2.4 Objective Function and Optimization -- 3 Experiment -- 3.1 Experiment Setup -- 3.2 Comparison with State-of-the-Art Methods -- 3.3 Parameter Analysis -- 3.4 Ablation Study -- 4 Conclusion -- References -- SMVT: Spectrum-Driven Multi-scale Vision Transformer for Referring Image Segmentation -- 1 Introduction.; 2 Related Works -- 3 Method -- 3.1 Overview -- 3.2 Cross-modal Feature Encoder -- 3.3 Spectrum-Driven Fusion Attention -- 3.4 Cross-modal Feature Refinement Enhancement Module -- 3.5 Prediction Mask and Loss Function -- 4 Experiments -- 4.1 Dataset and Evaluation Metrics -- 4.2 Implementation Details -- 4.3 Comparison with State-of-the-Art Methods -- 4.4 Ablation Study -- 5 Conclusion -- References -- GDCSF: Global Depth Convolution-Based Swin Framework for Electron Microscopy Pollen Image Classification -- 1 Introduction -- 2 Research Background -- 3 Methodology -- 3.1 Swin Transformer -- 3.2 Strip Convolution Scaling Module -- 3.3 Field Dual Bilateral Attention Module -- 3.4 Measurement -- 4 Experimental Results -- 4.1 Dataset -- 4.2 Experimental Settings -- 4.3 Experimental Results and Inference -- 4.4 Ablation Experiments -- 5 Conclusions -- References -- Adversarial Attack Against Convolutional ; Neural Network via Gradient Approximation -- 1 Introduction -- 2 Related Work -- 2.1 Notions -- 2.2 Convolutional Neural Network -- 2.3 Threat Model -- 3 Methodologies -- 3.1 Model Framework -- 3.2 Gradient Optimization -- 3.3 Adversarial Sample Generation -- 4 Experiments -- 4.1 Experimental Setups -- 4.2 Experimental Analysis -- 5 Conclusion -- References -- Hierarchical Cascaded Multi-Axis Window Self-Attention and Layer Feature Fusion for Brain Glioma Segmentation -- 1 Introduction -- 2 Related Work -- 3 Method Overview -- 3.1 Model Architecture -- 3.2 Hierarchical Cascaded Multi-Axis Window Self-Attention -- 3.3 Layer Feature Fusion -- 4 Experiments -- 4.1 Dataset -- 4.2 Training and Parameter Settings -- 4.3 Validation of the Effectiveness of the Hierarchical Cascaded Multi-Axis Window Self-Attention Component -- 4.4 Validation of the Effectiveness of the Layer Feature Fusion Component -- 4.5 Performance Comparison of Different Models.; 5 Conclusion.
• 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.

Advanced Intelligent Computing Technology and Applications : 21st International Conference, ICIC 2025, Ningbo, China, July 26–29, 2025, Proceedings, Part XXIV / / edited by De-Shuang Huang, Qinhu Zhang, Chuanlei Zhang, Wei Chen

• Record Nr.: UNISA996668463303316
• Pubbl/distr/stampa: Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2025
• ISBN: 981-9500-20-6
• Edizione: [1st ed. 2025.]
• Descrizione fisica: 1 online resource (XX, 521 p. 171 illus., 142 illus. in color.)
• Collana: Lecture Notes in Artificial Intelligence, , 2945-9141 ; ; 15865
• Disciplina: 006.3
• Soggetti: Computational intelligence; Computer networks; Machine learning; Application software; Computational Intelligence; Computer Communication Networks; Machine Learning; Computer and Information Systems Applications
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di contenuto: -- Natural Language Processing and Computational Linguistics. -- Mongolian Multimodal Sentiment Analysis Based on Multi-Level Attention and Convolution-Enhanced Fusion. -- Research on joint extraction of Chinese diabetes entity relations based on hybrid attention and hierarchical network. -- SSC-SQL: A Text-to-SQL Generation Framework with Multi-Process Collaboration. -- CoT Reasoning-Based Content Adaptation and Image Generation for Chinese Poetry. -- Self-Attentive CycleGAN for Damaged Khitan Script Reconstruction. -- A Hierarchical Prompt-Enhanced Mix-up Model with Graph Attention Networks for Academic Text Classification. -- Dynamic Neural Transfer for Domain-Level Zero-Shot Cognitive Diagnosis. -- Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations. -- LENS-RMHR: Enhancing Telecom Fraud Detection with Large Language Model Neuron Selection. -- ; GeneralCI: Do LLMs Have the Generalization Ability in Conducting Causal Inference. -- Multimodal Sentiment Analysis of Mongolian Language Based on Gated Transformer and Adaptive Hyper-modality. -- Towards a Concise Benchmark for Security Risk Evaluation in Large Language Models. -- Personalized Prompt Attack Strategies Against Large Language Models. -- MACCISA: A Multimodal Commonsense Knowledge Aware Model for Counterfactual Implicit Sentiment Analysis. -- Concept-Guided Persona Perception with Commonsense Reasoning for Personalized Dialogue Generation. -- Self-Distillation Model for Emotion Recognition with Cross-Modal Interaction and Graph Neural Networks. -- Talk the Talk, Debate the Bias: LLM Alignment via Role-Play Rumble. -- BERT-CHAB: Hierarchical Context Fusion with Adaptive Boundary Detection for Robust Chinese Named Entity Recognition in Noisy Social Media. -- Personalized Emotion Prediction Using Instruction-Tuned Large Language Models. -- BiCoT: Enhancing Large Language Model Reasoning Through Bidirectional Correction of Thought. -- MAF-CPR: LLM-Based Multi-Agent Framework for Complex Pull Request Review in GitHub. -- Definition Modeling for WSD and Semantic Perplexity-BERT Composite Score (SPBS). -- Syntax and Semantic Dual-Enhanced Chinese Named Entity Recognition. -- Improve Question Generation via Dual Perspective Key Phrase Selection. -- OptiACL: Optimized Anchor Contrastive Learning Framework for Multimodal Conversational Emotion Recognition. -- Implicit Validation Inference for Few-shot Named Entity Recognition. -- Token Memory Transformer with Infinite Context. -- FrameNet and Multiway Attention for Chinese Event Argument Extraction. -- CoT-NER: A Reasoning Method via Chain of Thought for Chinese Named Entity Recognition. -- Optimizing Knowledge Graph Reasoning via Global Relation Pruning with LLMs. -- Document-level Relation Extraction with Retrieval-Augmented. -- SARGAT: A Relation-Typed Graph Attention Network with Sentiment Distance-Aware Attention for Aspect-Based Sentiment Analysis. -- HierDaC: Detecting Long-Text Misinformation via Hierarchical Divide-and-Conquer. -- Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pretrained Priors. -- UOS-FSNER: Unified One-stage Few-shot Named Entity Recognition. -- HealthBridge: A Cross-lingual Clustering Framework for English-Chinese Health News. -- MedLite: a lightweight medical multimodal model based on knowledge distillation and inference optimization. -- Do Not Say It Directly: Generating Indirect Expressions with Large Language Models. -- ME-CWNER: Multi-metadata Embedding based Chinese Named Entity Recognition for Wheat Diseases and Pests. -- Join Social and Temporal Information for Rumor Detection. -- Advancing Low-Resource Machine Translation: A Unified Data Selection and Scoring Optimization Framework. -- Multi-modal Entity Linking Model based on Knowledge Distillation. -- A Semantic-Structural Synergistic Chunking Method for Enhancing Domain Specific LLM Fine-Tuning.
• Sommario/riassunto: The 20-volume set LNCS 15842-15861, together with the 4-volume set LNAI 15862-15865 and the 4-volume set LNBI 15866-15869, constitutes the refereed proceedings of the 21st International Conference on Intelligent Computing, ICIC 2025, held in Ningbo, China, during July 26-29, 2025. The 1206 papers presented in these proceedings books were carefully reviewed and selected from 4032 submissions. They deal with emerging and challenging topics in artificial intelligence, machine learning, pattern recognition, bioinformatics, and computational biology. .