Traj2Former: A Local Context-aware Snapshot and Sequential Dual Fusion Transformer for Trajectory Classification

Page view(s)
11
Checked on Dec 01, 2024
Traj2Former: A Local Context-aware Snapshot and Sequential Dual Fusion Transformer for Trajectory Classification
Title:
Traj2Former: A Local Context-aware Snapshot and Sequential Dual Fusion Transformer for Trajectory Classification
Journal Title:
Proceedings of the 32nd ACM International Conference on Multimedia
Keywords:
Publication Date:
28 October 2024
Citation:
Xie, Y., Zhang, Y., Yin, Y., Zhang, S., Zhang, Y., Shah, R., Zimmermann, R., & Xiao, G. (2024). Traj2Former: A Local Context-aware Snapshot and Sequential Dual Fusion Transformer for Trajectory Classification. Proceedings of the 32nd ACM International Conference on Multimedia, 8053–8061. https://doi.org/10.1145/3664647.3681340
Abstract:
The wide use of mobile devices has led to a proliferated creation of extensive trajectory data, rendering trajectory classification increasingly vital and challenging for downstream applications. Existing deep learning methods offer powerful feature extraction capabilities to detect nuanced variances in trajectory classification tasks. However, their effectiveness remains compromised by the following two unsolved challenges. First, identifying the distribution of nearby trajectories based on noisy and sparse GPS coordinates poses a significant challenge, providing critical contextual features to the classification. Second, though efforts have been made to incorporate a shape feature by rendering trajectories into images, they fail to model the local correspondence between GPS points and image pixels. To address these issues, we propose a novel model termed Traj2Former to spotlight the spatial distribution of the adjacent trajectory points (i.e., contextual snapshot) and enhance the snapshot fusion between the trajectory data and the corresponding spatial contexts. We propose a new GPS rendering method to generate contextual snapshots, but it can be applied from a trajectory database to a digital map. Moreover, to capture diverse temporal patterns, we conduct a multi-scale sequential fusion by compressing the trajectory data with differing rates. Extensive experiments have been conducted to verify the superiority of the Traj2Former model.
License type:
Publisher Copyright
Funding Info:
Singapore Ministry of Education Academic Research Fund Tier 2 under MOE’s official grant number T2EP20221-0023.

The Program of NSFC (Grant No. 62172157) and the Programs of Hunan Province (Grant Nos. 2024JJ2026, 2023GK2002).
Description:
© Owner/Author(s) 2024. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in MM '24: Proceedings of the 32nd ACM International Conference on Multimedia, http://dx.doi.org/10.1145/3664647.3681340.
ISBN:
979-8-4007-0686-8/24/10
Files uploaded:

File Size Format Action
traj2former.pdf 3.32 MB PDF Open