Trajectory Data
Trajectory data, encompassing the recorded movements of objects or individuals over time, is crucial for understanding diverse phenomena across various fields. Current research focuses on efficiently processing and analyzing this data, often employing deep learning models like LSTMs, Transformers, and Convolutional Neural Networks, to address challenges such as data imputation, prediction, and privacy preservation. These advancements are significantly impacting applications ranging from autonomous driving and urban planning to activity recognition and scientific discovery by enabling more accurate modeling and analysis of complex movement patterns.
Papers
DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
Guosheng Zhao, Chaojun Ni, Xiaofeng Wang, Zheng Zhu, Guan Huang, Xinze Chen, Boyuan Wang, Youyi Zhang, Wenjun Mei, Xingang Wang
Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models
Tangwen Qian, Junhe Li, Yile Chen, Gao Cong, Tao Sun, Fei Wang, Yongjun Xu