G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction

Zhang, Xinyue; Gong, Letian; Lin, Yan; Cheng, Jinjun; Zhang, Junlin; Yao, Guanyu; Guo, Shengnan; Lin, Youfang; Wang, Shaojiang; Wan, Huaiyu

doi:10.24963/ijcai.2026/360

G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction

Xinyue Zhang, Letian Gong, Yan Lin, Jinjun Cheng, Junlin Zhang, Guanyu Yao, Shengnan Guo, Youfang Lin, Shaojiang Wang, Huaiyu Wan

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3241-3249.

https://doi.org/10.24963/ijcai.2026/360

Keywords

Data Mining: Mining spatial and/or temporal data

Abstract

Generalized vehicle trajectory prediction across diverse junctions, including urban intersections and roundabouts, remains a fundamental task in Cooperative Vehicle–Infrastructure Systems (CVIS). This study faces two key challenges: (1) Generalize across junctions with heterogeneous map semantics and traffic behavioral patterns, where the former arises from differences in road topologies and traffic regulations, and the latter reflects diverse behavioral intentions of road users; (2) Scenario-adaptive interaction modeling, where single-modality trajectory learning captures local spatio-temporal correlation, but lacks map constraint and direction-aware interaction contexts. To overcome these challenges, we propose G-VTM, a generalized vision-trajectory model. G-VTM models fine-grained behavioral patterns and relative spatial interaction from trajectory modality. At the vision modality, G-VTM captures global map semantics while modeling scenario- and direction-aware interaction based on intuitive visual perception. Experiments on multiple real-world datasets collected by unmanned aerial vehicles (UAVs) demonstrate that our method achieves strong generalized performance under heterogeneous traffic conditions. The code is provided at https://github.

com/zxyhaclyon/G-VTM.

Xinyue Zhang, Letian Gong, Yan Lin, Jinjun Cheng, Junlin Zhang, Guanyu Yao, Shengnan Guo, Youfang Lin, Shaojiang Wang, and Huaiyu Wan. 2026. G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3241–3249. https://doi.org/10.24963/ijcai.2026/360

@inproceedings{ijcai2026p360,
  title     = {G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction},
  author    = {Zhang, Xinyue and Gong, Letian and Lin, Yan and Cheng, Jinjun and Zhang, Junlin and Yao, Guanyu and Guo, Shengnan and Lin, Youfang and Wang, Shaojiang and Wan, Huaiyu},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {3241--3249},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/360},
  url       = {https://doi.org/10.24963/ijcai.2026/360},
}

TY  - CPAPER
TI  - G-VTM: A Multimodal Vision-Trajectory Model for Generalized Vehicle Trajectory Prediction
AU  - Zhang, Xinyue
AU  - Gong, Letian
AU  - Lin, Yan
AU  - Cheng, Jinjun
AU  - Zhang, Junlin
AU  - Yao, Guanyu
AU  - Guo, Shengnan
AU  - Lin, Youfang
AU  - Wang, Shaojiang
AU  - Wan, Huaiyu
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 3241
EP  - 3249
DO  - 10.24963/ijcai.2026/360
UR  - https://doi.org/10.24963/ijcai.2026/360
ER  -