This book constitutes the refereed proceedings of the 9th International Symposium Conference on Artificial Intelligence and Robotics, ISAIR 2024, in Guilin, China, in September 2730, 2024.

The 61 full papers presented were carefully reviewed and selected from a total of 164 submissions. The ISAIR 2024 focuses on three important areas of pattern recognition: artificial intelligence, robotics and Internet of Things, covering various technical aspects.

Inhalt

.- A lane detection method based on fusion of large kernel attentionmechanism.

.- A Study on Enhancing Graph-Based Knowledge Tracing through Question Interaction.

.- Radiology report generation based on multi-scale feature fusion and enhancement.

.- Spatio-Temporal Focus with Active Learning in Sparse Black-Box Adversarial Attacks for Video Recognition.

.- An Improved Point Cloud Registration Algorithm Based on Feature Point Extraction.

.- YOLOv8-FGE: A lightweight mouse behavior detection algorithm.

.- A Dual Encoder U-Net for Multi-Scale 3D Medical Image Segmentation.

.- A Gas Concentration Prediction Model Based on SBLPformer.

.- A MOTRv2-based UAV multi-target tracking model EL-MOTR.

.- Prediction of Typhoon Cloud Maps Based on Self Attention Memory Spatiotemporal Model.

.- Information-theoretic Deep Quantification for Unsupervised Cross-modal Hashing.

.- Research on SwinT-SOLOv2 Modeling for Instance Segmentation.

.- An Overview of Abnormal Data Recovery in Power Systems.

.- An Overview of Full-cycle Data Security For Drone Inspection.

.- A Restoration Method Based on Color Compensation and Depth Prior Using a Revised Underwater Imaging Model.

.- Real-time Student Behavior Analysis via YOLOv5 with Coordinate Attention.

.- GD-RRT: An Improved RRT Path Planning Algorithm Combining Gaussian Distributed Sampling and Depth Strategy for fruit-picking robot.

.- UAV Swarm Air Combat Strategies Research based on Multi-Agent Reinforcement Learning and Rule Coupling.

.- Photovoltaic Power Prediction Based on Machine Learning Fusion Algorithm.

.- Multi-modal Spatio-Temporal Transformer for Defect Recognition of Substation Equipment.

.- A Comprehensive Cross-Phase Feature Fusion Method for Multi-phase Liver Tumor Segmentation in Enhanced CT Images.

.- OneStar: Efficient Template-Separable Hierarchical Transformer Tracking for Edge Computing.

.- A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries.

.- Mitigating Multimodal Large Language Model Hallucinations through Direct Preference Optimization.

.- Briefness-Oriented prompting elicits faithfulness in LVLM.

.- A Novel Group Block Attention Module for Lung CT Image Segmentation.

.- Layered Clothing Detection Based on Improved YOLOV9.

.- Strategic Medical Text Classification with Improved Blending Ensemble Learning.

.- HDCP: Hierarchical Dual Cross-modality Prompts Guided RGB-D Fusion for 6D Object Pose Estimation.

.- Dense Images Of Honey Bees.

.- Application of an Improved Residual Attention Neural Network in Mechanical Part Classification.

.- Genetic Algorithm-Optimized Random Forest for Grid Fault Prediction.