Yu / Chen / Shi | Intelligence Science and Technology | Buch | 978-981-9295-64-7 | www.sack.de

Buch, Englisch, 624 Seiten, Format (B × H): 155 mm x 235 mm

Reihe: Communications in Computer and Information Science

Yu / Chen / Shi

Intelligence Science and Technology

First International Conference on Intelligence, ICI 2026, Zhuhai, China, May 8–10, 2026, Proceedings, Part II
Erscheinungsjahr 2027
ISBN: 978-981-9295-64-7
Verlag: Springer

First International Conference on Intelligence, ICI 2026, Zhuhai, China, May 8–10, 2026, Proceedings, Part II

Buch, Englisch, 624 Seiten, Format (B × H): 155 mm x 235 mm

Reihe: Communications in Computer and Information Science

ISBN: 978-981-9295-64-7
Verlag: Springer


This book constitutes the proceedings of the First International Conference on Intelligence Science and Technology, ICI 2026, held in Zhuhai, China, during May 8–10, 2026.

The 239 full papers presented in these proceedings were carefully reviewed and selected from 563 submissions. The papers are organized in the following topical sections:

Part I: Session 1. Computer Vision and Multimodal Perception; Session 2. Large Language Models, Knowledge Graphs, and Human-AI Interaction; Session 3. Optimization, Planning, and Decision Intelligence; Session 4. Distributed and Edge Intelligence; Session 5. Scientific Forecasting, Biomedical, and Social Analytic.
Part II: Session 1. Visual Perception and Sensing Systems; Session 2. Efficient LLM and Foundation Model Systems; Session 3. Knowledge Graphs, Recommendation, and Social Intelligence; Session 4. Predictive Optimization and Adaptive Intelligence; Session 5. Applied Safety, Health, and Signal Intelligence.
Part III: Session 1 .- Knowledge, Retrieval, and LLM Reasoning Knowledge-Structured; Session 2 .- Vision, Sensing, and Imaging Intelligence; Session 3 .- Multimodal Human-Centered Intelligence; Session 4 .- Optimization, Scheduling, and Decision Intelligence; Session 5 .- Security, Robustness, and Trustworthy AI.
Part IV: Session 1. Computer Vision and Imaging Intelligence; Session 1. Computer Vision and Imaging Intelligence; Session 3. Human-Centered and Applied Social Intelligence; Session 4. Knowledge, Retrieval, and Reasoning with LLMs; Session 5. Security, Robustness, and Trustworthy AI.
Part V: Session 1. Trust, Security, and Privacy for AI; Session 2. Vision, Imaging, and Medical Intelligence; Session 3. Human-Centered Decision Support and Social Systems;  Session 4. Graph, Federated, and Knowledge-Driven Intelligence; Session 5. Optimization, Frontier AI Theory, and Financial Intelligence. 

Yu / Chen / Shi Intelligence Science and Technology jetzt bestellen!

Zielgruppe


Research

Weitere Infos & Material


.- Session 1. Visual Perception and Sensing Systems.
.- A Deep Learning Framework for Kinematic Analysis and Action Quality Assessment of the Shoulder Press Using Spatiotemporal Focus and BiLSTM Networks.
.- RoadSAM-PF: A Prompt-Free Dual-Branch Adaptation of SAM for Road Extraction from Remote Sensing Images.
.- Global Residual Learning and Dual-Domain Attention for High-Fidelity Endoscopic Image Enhancement.
.- EGD-YOLO: An Efficient Vehicle Surface Defect Detection Algorithm Based on Geometric Perception and Multi-scale Fusion.
.- YOLOv8 Optimization with BiFPN-AFE and Occlusion-Adaptive DeepLabV3+ for Camellia Oleifera Fruit Detection.
.- An Embodied Intelligence-Enhanced Multi-Objective Optimization Framework for Video Stream-Based Vehicle State Detection.
.- Depression Recognition via Joint Analysis of Facial Expressions and Risky Behaviors Using YOLOv8.
.- MATNet: Multi-task Adversarial Transformer Network for Road Anomaly Detection with Image Restoration.
.- Deep Learning for Precise Differentiation of Severe Pediatric Pneumonia: A Transfer Learning Approach Using Vision Transformers.
.- Crack Detection Based on RCGS-YOLOv8 Algorithm with UAV Collaboration.
.- Session 2. Efficient LLM and Foundation Model Systems.
.- Accelerating Cloud-Device Collaborative Speculative Decoding via Cloud-Guided Sparse Attention.
.- Heterogeneity-Aware Post-Training Quantization for Multimodal Mamba LLMs.
.- SOLHead: Orthogonal Low-Rank Classification Heads for Multi-Label Text Classification.
.- Dual-Anchor Pruning: Exploiting Cross-Layer Attention Evolution for Efficient VLM Inference.
.- Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge.    
.- AdaQServe: Adaptive Kernel Scheduling for Quantized Large Language Model Serving.
.- Who Will Attack: Group Sport Activity Prediction.
.- A Fusion Model of Lightweight CNN and LSTM for the Evaluation of New-Quality Productive Force Impact on City Economic Development.
.- Enhancing Long-Tail Recommendation via Large Language Models and Neighborhood Information.
.- Cuckoo Algorithm Based on TR Algorithm and Improved Probability Parameter.
.- Session 3. Knowledge Graphs, Recommendation, and Social Intelligence.
.- Expert-Guided incomplete preference estimation and consistency enhancement via a discretized hierarchical conditional variational autoencoder.
.- GMoPE: A Prompt-Expert Mixture Framework for Graph Foundation Models.
.- FairLoop: Iterative Fair Recommendation via Multi-objective Optimization.
.- Multi-Granularity Representation Learning with Semantically-Enhanced Coarsening for Text-Attribute Graphs.
.- Multimodal Visual Communication Strategy of Zhuhai Study Abroad Culture IP Under the Guidance of Party Building: A Knowledge Graph-Driven Intelligent Analysis.    
.- Research on a Two-Way Reciprocal Recommendation Algorithm for Graduates Considering Dynamic Supply and Demand Balance.
.- Social Link Prediction Based on LLM-Augmented Graph Neural Network Models.
.- Research on Multimodal Heterogeneous Feature Fusion and APT Attack Traceback Method for Complex Network Scenarios.
.- Construction of a Three-Dimensional Teaching Defense System in Higher Education for AI Hallucination Risks.    
.- Research on Financial Crisis Early Warning of Chinese Listed Companies Based on HPSO-SVM Model.
.- Session 4. Predictive Optimization and Adaptive Intelligence.
.- Multi-scale Variational Autoencoder with Short-Long Term Structure for Multivariate Time Series Anomaly Detection.
.- Bi-LSTM Behavior Recognition Based on the Synergy of Mutual Information Entropy and Enhanced Attention Mechanism.
.- High Throughput VL-MoE Inference on Resource-Constrained Hardware via Heterogeneous ZigZag Scheduling.
.- Physically-Consistent Cascade Hydropower Scheduling: A Hybrid MILP-GA Framework with Explicit Hydrodynamic Coupling.
.- Dmhybrid: Deep learning traffic flow prediction model based on Decomposition-Memory-Mixing.
.- LSMT-based portfolio optimization with transaction costs.
.- FastMA: Efficient Memory-Agent Serving via Prefix-Sharing and Overlapped Pipeline.
.- Entropy Driven Source-Free Domain Generalization.
.- Exploring Cross-Domain Transfer with Unified Multitask Pre-training on Material and Physics Time Series.
.- Session 5. Applied Safety, Health, and Signal Intelligence.
.- Smooth Adversarial Domain Adaptation for Cross-Domain Ship-Radiated Noise Recognition.
.- Safety-Aware Tracking with Foundation Models and PPO.
.- Cross-Environment WiFi-Based 3D Human Pose Estimation via Domain Generalization.
.- Domain-Specific Text Anonymization Based on Local Language Models.
.- Fast-Deploy WiFi Trajectory Tracking via Homography Calibration and Spatiotemporal Feature Fusion.
.- A Heterogeneous Neural Network Model for Failure Analysis of Optical Modules.
.- Deciphering the Causal Nexus of Gut Microbiota, Serum Metabolites, and Graves' Disease: A Mendelian Randomization Analysis.
.- Predicting Olympic Medal Distribution with Random Forest and Coach Effect Analysis.
.- Wide-temporal Category Sentiment Recognition of Audio and Text based on Transfer Learning.



Ihre Fragen, Wünsche oder Anmerkungen
Vorname*
Nachname*
Ihre E-Mail-Adresse*
Kundennr.
Ihre Nachricht*
Lediglich mit * gekennzeichnete Felder sind Pflichtfelder.
Wenn Sie die im Kontaktformular eingegebenen Daten durch Klick auf den nachfolgenden Button übersenden, erklären Sie sich damit einverstanden, dass wir Ihr Angaben für die Beantwortung Ihrer Anfrage verwenden. Selbstverständlich werden Ihre Daten vertraulich behandelt und nicht an Dritte weitergegeben. Sie können der Verwendung Ihrer Daten jederzeit widersprechen. Das Datenhandling bei Sack Fachmedien erklären wir Ihnen in unserer Datenschutzerklärung.