A5116548941- Video Surveillance and Tracking Methods
- Autonomous Vehicle Technology and Safety
- Advanced Image and Video Retrieval Techniques
- Traffic and Road Safety
- Click Chemistry and Applications
- Anomaly Detection Techniques and Applications
- Computational Drug Discovery Methods
- Traffic Prediction and Management Techniques
- Bioinformatics and Genomic Networks
Tsinghua University
2025
University of Toronto
2024
Precise quantification of protein-ligand interaction is critical in early-stage drug discovery. Artificial intelligence (AI) has gained massive popularity this area, with deep-learning models used to extract features from ligand and protein molecules. However, these often fail capture intermolecular non-covalent interactions, the primary factor influencing binding, leading lower accuracy interpretability. Moreover, such overlook spatial structure complexes, resulting weaker generalization....
The field of trajectory forecasting has grown significantly in recent years, partially owing to the release numerous large-scale, real-world human datasets for autonomous vehicles (AVs) and pedestrian motion tracking. While such have been a boon community, they each use custom unique data formats APIs, making it cumbersome researchers train evaluate methods across multiple datasets. To remedy this, we present trajdata: unified interface At its core, trajdata provides simple, uniform,...
Understanding road geometry is a critical component of the autonomous vehicle (AV) stack. While high-definition (HD) maps can readily provide such information, they suffer from high labeling and maintenance costs. Accordingly, many recent works have proposed methods for estimating HD online sensor data. The vast majority approaches encode multi-camera observations into an intermediate representation, e.g., bird's eye view (BEV) grid, produce vector map elements via decoder. this architecture...