My CV
Orcid
Researcherid
Kaggle
ResearchGateAbout Me
Here is Tianze Zhang (张天泽).
I’m an undergraduate student majoring in CS at the University of Melbourne. Previously, I served as a research assistant at the Xinjiang Key Laboratory of Signal Detection and Processing, advised by Prof. Gang Shi, and I still keep in close contact with the lab. I also spent a great summer research project at the University of Hong Kong with Prof. Heming Cui.
If you are interested in any aspect of me, I would love to chat and collaborate, please email me at - zhangtianze.unimelb[at]gmail.com
Research Interests
- Natural Language Processing
- Applied Machine Learning
- Computer Vision
- Computational Law
- Quantitative Analysis
My current research focuses on practical problems faced by artificial intelligence in complex legal scenarios. My interests are Machine Learning and its applications in Law, Finance, and Medicine. In short, advanced technologies such as artificial intelligence have a positive impact on everyone’s life. I hope to devote my talents to this meaningful cause and bring benefits to society.
News and Updates
Our paper was accepted by IJCNN2025
Our research result "SWR-BIDeN: An Improved BIDeN Model for Severe Weather Removal in Image Processing" was accepted by the International Joint Conference on Neural Networks (IJCNN2025). The model achieved advanced performance in image restoration tasks under severe weather conditions such as heavy rain and haze.
Our paper was accepted by ICIC2025
Our research result "LightDrone-YOLO: A Novel Lightweight and Efficient Object Detection Network for Unmanned Aerial Vehicles" was accepted by the International Conference on Intelligent Computing (ICIC2025). This model significantly reduces the computational complexity while maintaining high accuracy, and is suitable for resource-constrained UAV platforms.
Our paper was accepted by ICIC2025
Our research result "Lightweight Remote Sensing Image Change Detection Based on Global Feature Fusion" was accepted by the International Conference on Intelligent Computing (ICIC2025). This method significantly reduces the computational complexity while maintaining high accuracy.
Our paper was accepted by ICIC2025
Our research result "GlintNet: A Lightweight Global-Local Integration Network with Spatial-Channel Mixed Attention for ReID" was accepted by the International Conference on Intelligent Computing (ICIC2025). The model has reached advanced levels in multiple pedestrian re-identification benchmarks.