Teacher, ZaoZhuang University, China
Profile
Orcid
🎓 Education:
Li Sai earned his PhD in Physical Electronics from the Shanghai Institute of Technical Physics, part of the Chinese Academy of Sciences. His academic journey is distinguished by his deep engagement in computer vision, artificial intelligence, and machine perception.
đź’Ľ Experience:
Currently associated with a leading research institution, Li Sai contributes significantly to the field of hyperspectral imaging and LiDAR data classification. His extensive research and collaborations have bolstered his reputation as an expert in these domains.
🔬 Research Interests:
Li Sai’s research interests include computer vision, artificial intelligence, machine perception, and the integration of semi-supervised learning techniques for image data. His work often intersects with the development of innovative algorithms to optimize data classification methods and enhance the performance of image recognition systems.
🏆 Awards:
Li Sai has been recognized for his academic contributions and was notably awarded the Shandong Provincial Natural Science Youth Fund in 2022 for his project on estimating wheat growth and yield using hyperspectral UAV imagery.
đź“ť Publications Top Notes:
Li Sai; Huang Shuo; AFA-Mamba: Adaptive Feature Alignment with Global-Local Mamba for Hyperspectral and LiDAR Data Classification*, Remote Sensing, 2024, 16(21). Read here – Focuses on advanced classification techniques merging hyperspectral and LiDAR data.
Sai Li; Peng Kou; Miao Ma; Haoyu Yang; Shuo Huang; Zhengyi Yang; Application of Semi-supervised Learning in Image Classification: Research on Fusion of Labeled and Unlabeled Data*, IEEE ACCESS, 2024. Read here – Highlights innovations in semi-supervised learning for image classification.
Zhiguo Li; Lingbo Li; Xi Xiao; Jinpeng Chen; Nawei Zhang; Sai Li; Low Sample Image Classification Based on Intrinsic Consistency Loss and Uncertainty Weighting Method*, IEEE ACCESS, 2023, 11: 49059-49070. Read here – Explores image classification using novel loss functions and weighting methods to manage data uncertainty.