Lei Ju
AI Data Scientist/Postdoctoral Computational Biologist
Research group: Artificial intelligence and data sciences
Biography
I hold a PhD from the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, specialising in computer vision, supervised and unsupervised learning, vision-language models (VLMs), knowledge distillation and large language models (LLMs). My postdoctoral research focuses on applying AI to agricultural challenges, including satellite-based crop monitoring and plant variety identification. I lead and contribute to interdisciplinary projects aimed at enhancing the scalability and accuracy of deep learning models for real-world field applications.
Publications
Publication
Quantifying tree-level peach flowering dynamics using UAV imagery and an optimized instance segmentation model
Date: 15 July 2025
Contributors: Qing Gu, Jiayu Cheng, Minghao Zhang, Xiongwei Li, Robert Jackson, Lei Ju, Weidong Lou, Miaojin Chen, Ji Zhou, Xiaobin Zhang
Journal: Computers and Electronics in Agriculture
Publication
Ada2 NPT: An Adaptive Nearest Proxies Triplet Loss for Attribute-Aware Face Recognition with Adaptively Compacted Feature Learning
Date: 22 April 2024
Contributors: Lei Ju, Zhanhua Feng, Muhammad Awais, Josef Kittler
Journal: Proceedings of the 15th Asian Conference on Machine Learning
Publication
Keep an eye on faces: Robust face detection with heatmap-Assisted spatial attention and scale-Aware layer attention
Date: 1 August 2023
Contributors: Lei Ju, Josef Kittler, Muhammad Awais Rana, Wankou Yang, Zhenhua Feng
Journal: Pattern Recognition
Publication
Dense Facial Landmark Localization: database and annotation tool
Date: 5 August 2019
Contributors: Lei Ju, Xiangyu Zhu, Zhen Lei, Xinfang Cui, Wankou Yang, Changyin Sun
Journal: 34rd Youth Academic Annual Conference of Chinese Association of Automation
Publication
GPCA-SIFT: A New Local Feature Descriptor for Scene Image Classification
Date: 22 October 2016
Contributors: Lei Ju, Ke Xie, Hao Zheng, Baochang Zhang, Wankou Yang
Journal: Pattern Recognition