• Dimensionality reduction and feature extraction/selection (降维与特征提取/选择)
  
• Spectral unmixing and endmember extraction (光谱解混与端元提取)
  
• Super-resolution and multimodal data fusion (超分辨率重建与多模态数据融合)
  
• Classification, clustering, and target/anomaly detection (分类、聚类及目标/异常检测)
  
• Deep learning and physics-informed neural networks for hyperspectral analysis (高光谱分析中的深度学习与物理引导神经网络)
  
• Compressive sensing and computational hyperspectral imaging (压缩感知与计算高光谱成像)
  
• Denoising, restoration, and quality enhancement (去噪、复原与质量增强)
  
• Real-time and embedded processing (实时与嵌入式处理)
  
• Applications in agriculture, environmental monitoring, mineralogy, food safety, medical diagnostics, cultural heritage, and defense (农业、环境监测、矿物学、食品安全、医学诊断、文化遗产及国防等应用)

Advances in hyperspectral data analysis and processing are reshaping remote sensing, biomedical imaging, industrial inspection, and other related fields. This track highlights the latest methodologies, algorithms, and applications that tackle the core challenges of hyperspectral data, including but not limited to high dimensionality, spectral variability, mixed pixels, and heavy computational demands. We especially welcome contributions that bridge theoretical advances with practical validation, as well as work that ventures into new application domains. The session offers a forum for interdisciplinary exchange and aims to help shape the future directions of hyperspectral data analysis.