Topic: Spatiotemporal Data Mining, Representation Learning, Trajectory Data Mining
This project explores how to generate high-quality spatial-temporal trajectory data and corresponding representations to address sparsity-related issues, thereby supporting a variety of downstream tasks.
My major contributions include:
- I conceived the core idea for this project, leading the proposal writing and contributing substantially to its content.
- I developed a representation learning approach to address label sparsity in trajectory mining, with results published in MMTEC.
- I mentored two PhD students (Tonglong Wei and Letian Gong) in our research group, collaborating on the design of methods for representation learning, imputation, and generation of human and vehicle trajectories. Results published in MM-STGED, IAGCN, and CACSR.