Trajectory Similarity Estimation via Geometry-Aligned InfoNCE: A Self-Supervised Framework With Multi-Factor Features and Robust Augmentations

Reliable trajectory similarity estimation underpins applications such as map matching, mobility anomaly detection, and travel behavior analysis. However, traditional distance-based methods are computationally expensive and sensitive to irregular sampling, while learning-based approaches, though more...

Whakaahuatanga katoa

Ngā taipitopito rārangi puna kōrero

Ngā kaituhi matua:	Fengqi Hao, Conghui Gao, Yawen Hou, Jinqiang Bai, Yongshun Gong, Hoiio Kong, Xiangjun Dong
Hōputu:	Artigo
Reo:	Inglês
I whakaputaina:	IEEE 2026-01-01
Rangatū:	IEEE Access
Ngā marau:	Contrastive representation learning geometric consistency geometry-aligned InfoNCE multi-factor feature extraction self-supervised learning spatio-temporal data mining
Urunga tuihono:	https://ieeexplore.ieee.org/document/11482131/
Ngā Tūtohu:	Tāpirihia he Tūtohu Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!