---
title: "DASS: A Dual-Branch Attention-based Framework for Trajectory Similarity Learning with Spatial and Semantic Fusion"
authors:
  - "Jiayi Li"
  - "Junhua Fang"
  - "Pingfu Chao"
  - "Jiajie Xu"
  - "Pengpeng Zhao"
doi: "10.24963/ijcai.2025/833"
url: "https://ijcai.org/proceedings/2025/833"
pdf: "https://ijcai.org/proceedings/2025/0833.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "7491-7499"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: MTA: Transportation"
---

# DASS: A Dual-Branch Attention-based Framework for Trajectory Similarity Learning with Spatial and Semantic Fusion

Jiayi Li, Junhua Fang, Pingfu Chao, Jiajie Xu, Pengpeng Zhao

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 7491-7499. DOI: [10.24963/ijcai.2025/833](https://doi.org/10.24963/ijcai.2025/833)

## Abstract

Trajectory similarity aims to identify pairs of similar trajectories, serving as a crucial operation in spatial-temporal data mining. Although several approaches have been proposed, they encounter the following two issues: 1) An overemphasis on spatial similarity in road networks while the rich semantic information embedded in trajectories is not fully exploited; 2) Dependence on Recurrent Neural Network (RNN) architectures would struggle to capture long-term dependencies. To address these limitations, we propose a Dual-branch Attention-based framework with Spatial and Semantic information (DASS) based on self-supervised learning. Specifically, DASS comprises two core components: 1) A trajectory representation module that models spatial-temporal adjacent relationships in the form of graph and converts semantics into numerical embeddings. 2) A backbone encoder with a co-attention module to independently process two features before they are integrated. Extensive experiments on real-world datasets demonstrate that DASS outperforms state-of-the-art methods, establishing itself as a novel paradigm.