UniTE: A Survey and Unified Pipeline for Pre-Training Spatiotemporal Trajectory Embeddings

Y Lin, Z Zhou, Y Liu, H Lv, H Wen, T Li… - … on Knowledge and …, 2024 - ieeexplore.ieee.org
Spatiotemporal trajectories are sequences of timestamped locations, which enable a variety
of analyses that in turn enable important real-world applications. It is common to map …

Causality-Augmented generalization network with cross-domain meta-learning for interlayer slip** recognition in viscoelastic sandwich structures

R Hou, Z Zhang, J Chen, Z Liu, L Tu - Mechanical Systems and Signal …, 2025 - Elsevier
Accurate interlayer slip** recognition in viscoelastic sandwich structures (VSSs) is critical
for mechanical equipment's safety and reliability. However, significant domain shifts exist in …

AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks

Q Wang, Y **a, S ZHong, W Li, Y Wu, S Cheng… - arxiv preprint arxiv …, 2025 - arxiv.org
Monitoring real-time air quality is essential for safeguarding public health and fostering
social progress. However, the widespread deployment of air quality monitoring stations is …

UniTE: A Survey and Unified Pipeline for Pre-training ST Trajectory Embeddings

Y Lin, Z Zhou, Y Liu, H Lv, H Wen, T Li, Y Li… - arxiv preprint arxiv …, 2024 - arxiv.org
Spatio-temporal (ST) trajectories are sequences of timestamped locations, which enable a
variety of analyses that in turn enable important real-world applications. It is common to map …

Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models

T Qian, J Li, Y Chen, G Cong, T Sun, F Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Modeling trajectory data with generic-purpose dense representations has become a
prevalent paradigm for various downstream applications, such as trajectory classification …

Nature Makes No Leaps: Building Continuous Location Embeddings with Satellite Imagery from the Web

X Hao, W Chen, X Zou, Y Liang - THE WEB CONFERENCE 2025 - openreview.net
Building location embedding from web-sourced satellite imagery has emerged as an
enduring research focus in web mining. However, most existing methods are inherently …