TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation

• URL: http://arxiv.org/abs/2506.15898v1
• Date: Wed, 18 Jun 2025 21:52:07 GMT
• Title: TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation
• Authors: Xiao Zhang, Xingyu Zhao, Hong Xia, Yuan Cao, Guiyuan Jiang, Junyu Dong, Yanwei Yu,
• Abstract summary: We propose a novel trajectory similarity computation framework, named TrajDiff.<n>Specifically, TrajDiff relies on cross-attention and an attention score mask mechanism with adaptive fusion.<n>Extensive experiments on three publicly available datasets show that TrajDiff consistently outperforms state-of-the-art baselines.
• Score: 39.42796455901991
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the proliferation of location-tracking technologies, massive volumes of trajectory data are continuously being collected. As a fundamental task in trajectory data mining, trajectory similarity computation plays a critical role in a wide range of real-world applications. However, existing learning-based methods face three challenges: First, they ignore the semantic gap between GPS and grid features in trajectories, making it difficult to obtain meaningful trajectory embeddings. Second, the noise inherent in the trajectories, as well as the noise introduced during grid discretization, obscures the true motion patterns of the trajectories. Third, existing methods focus solely on point-wise and pair-wise losses, without utilizing the global ranking information obtained by sorting all trajectories according to their similarity to a given trajectory. To address the aforementioned challenges, we propose a novel trajectory similarity computation framework, named TrajDiff. Specifically, the semantic alignment module relies on cross-attention and an attention score mask mechanism with adaptive fusion, effectively eliminating semantic discrepancies between data at two scales and generating a unified representation. Additionally, the DDBM-based Noise-robust Pre-Training introduces the transfer patterns between any two trajectories into the model training process, enhancing the model's noise robustness. Finally, the overall ranking-aware regularization shifts the model's focus from a local to a global perspective, enabling it to capture the holistic ordering information among trajectories. Extensive experiments on three publicly available datasets show that TrajDiff consistently outperforms state-of-the-art baselines. In particular, it achieves an average HR@1 gain of 33.38% across all three evaluation metrics and datasets.

Related papers

• A Data-Centric Approach to 3D Semantic Segmentation of Railway Scenes [0.0]
  This paper introduces two targeted data augmentation methods to improve segmentation performance on the railway-specific OSDaR23 dataset.<n>The person instance pasting method enhances segmentation of pedestrians at distant ranges by injecting realistic variations into the dataset.<n>The track sparsification method redistributes point density in LiDAR scans, improving track segmentation at far distances with minimal impact on close-range accuracy.
  arXiv  Detail & Related papers  (2025-04-25T09:46:31Z)
• Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory [53.37473225728298]
  The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data. Matching Training Trajectories (MTT) has been a prominent approach, which replicates the training trajectory of an expert network on real data with a synthetic dataset. We introduce a novel method called Matching Convexified Trajectory (MCT), which aims to provide better guidance for the student trajectory.
  arXiv  Detail & Related papers  (2024-06-28T11:06:46Z)
• More Than Routing: Joint GPS and Route Modeling for Refine Trajectory Representation Learning [26.630640299709114]
  We propose Joint GPS and Route Modelling based on self-supervised technology, namely JGRM. We develop two encoders, each tailored to capture representations of route and GPS trajectories respectively. The representations from the two modalities are fed into a shared transformer for inter-modal information interaction.
  arXiv  Detail & Related papers  (2024-02-25T18:27:25Z)
• Weakly-supervised 3D Pose Transfer with Keypoints [57.66991032263699]
  Main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with different topologies. We propose a novel weakly-supervised keypoint-based framework to overcome these difficulties.
  arXiv  Detail & Related papers  (2023-07-25T12:40:24Z)
• DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model [44.490978394267195]
  We propose a spatial-temporal probabilistic model for trajectory generation (DiffTraj) The core idea is to reconstruct and synthesize geographic trajectories from white noise through a reverse trajectory denoising process. Experiments on two real-world datasets show that DiffTraj can be intuitively applied to generate high-fidelity trajectories.
  arXiv  Detail & Related papers  (2023-04-23T08:42:45Z)
• Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics [30.9735101687326]
  Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. Existing TRL works usually treat trajectories as ordinary sequence data, while some important spatial-temporal characteristics, such as temporal regularities and travel semantics, are not fully exploited. We propose a novel Self-supervised trajectory representation learning framework with TemporAl Regularities and Travel semantics, namely START.
  arXiv  Detail & Related papers  (2022-11-17T13:14:47Z)
• 3DMODT: Attention-Guided Affinities for Joint Detection & Tracking in 3D Point Clouds [95.54285993019843]
  We propose a method for joint detection and tracking of multiple objects in 3D point clouds. Our model exploits temporal information employing multiple frames to detect objects and track them in a single network.
  arXiv  Detail & Related papers  (2022-11-01T20:59:38Z)
• DouFu: A Double Fusion Joint Learning Method For Driving Trajectory Representation [13.321587117066166]
  We propose a novel multimodal fusion model, DouFu, for trajectory representation joint learning. We first design movement, route, and global features generated from the trajectory data and urban functional zones. With the global semantic feature, DouFu produces a comprehensive embedding for each trajectory.
  arXiv  Detail & Related papers  (2022-05-05T07:43:35Z)
• Roadside Lidar Vehicle Detection and Tracking Using Range And Intensity Background Subtraction [0.0]
  We present the solution of roadside LiDAR object detection using a combination of two unsupervised learning algorithms. The method was validated against a commercial traffic data collection platform.
  arXiv  Detail & Related papers  (2022-01-13T00:54:43Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction [110.61383502442598]
  We introduce a novel neural network framework termed Cross-Modal Message Propagation Network (CMMPNet) CMMPNet is composed of two deep Auto-Encoders for modality-specific representation learning and a tailor-designed Dual Enhancement Module for cross-modal representation refinement. Experiments on three real-world benchmarks demonstrate the effectiveness of our CMMPNet for robust road extraction.
  arXiv  Detail & Related papers  (2021-11-30T04:30:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.