paper-with-me

홈 › Papers

TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis

2025-06-19 · Chunhou Ji, Qiumeng Li

GPS trajectory data reveals valuable patterns of human mobility and urban dynamics, supporting a variety of spatial applications. However, traditional methods often struggle to extract deep semantic representations and incorporate contextual map information. We propose TrajSceneLLM, a multimodal perspective for enhancing semantic understanding of GPS trajectories. The framework integrates visualized map images (encoding spatial context) and textual descriptions generated through LLM reasoning (capturing temporal sequences and movement dynamics). Separate embeddings are generated for each modality and then concatenated to produce trajectory scene embeddings with rich semantic content which are further paired with a simple MLP classifier. We validate the proposed framework on Travel Mode Identification (TMI), a critical task for analyzing travel choices and understanding mobility behavior. Our experiments show that these embeddings achieve significant performance improvement, highlighting the advantage of our LLM-driven method in capturing deep spatio-temporal dependencies and reducing reliance on handcrafted features. This semantic enhancement promises significant potential for diverse downstream applications and future research in geospatial artificial intelligence. The source code and dataset are publicly available at: https://github.com/februarysea/TrajSceneLLM.

📄 PDF Abstract BibTeX arXiv:2506.16401

Code (1)

februarysea/trajscenellm 공식 구현 pytorch

Tasks

Temporal Sequences

Methods 이 논문이 사용한 방법론

GPS Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with…

Similar Papers 제목 키워드 기반

Holistic Semantic Representation for Navigational Trajectory Generation

2025-01-06 · Ji Cao, Tongya Zheng, Qinghong Guo, Yu Wang 외

Trajectory generation has garnered significant attention from researchers in the field of spatio-temporal analysis, as it can generate substantial synthesized human mobility trajectories that enhance user privacy and all…

Few-Shot LearningZero-Shot Learning

Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition

2026-07-16 · Linyun Xiang, Mark Neerincx, Stephanie Tan arxiv

Existing text summarization research has focused much on monologic information (e.g., newspaper articles, reports) without accounting for the interaction between speakers or authors. In contrast, dialogues are a rich com…

Text Summarization

Spotlight on Token Perception for Multimodal Reinforcement Learning

2025-10-10 · Siyuan Huang, Xiaoye Qu, Yafu Li, Yun Luo 외 arxiv

While Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Vision-Language Models (LVLMs), most existing methods in multimodal reasoning neglect the critical role of visu…

Reinforcement LearningMultimodal Reasoning

Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning

2025-10-16 · Ji Cao, Yu Wang, Tongya Zheng, Jie Song 외 arxiv

Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis. Fr…

Representation LearningTravel Time Estimation

CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation

2026-05-12 · Daohan Su, Hao Liu, Xunkai Li, Yinlin Zhu 외 arxiv

Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs, yet most existing approaches rely on tightly coupled architectures that suffer from prohibitive computa…

Representation LearningGraph Learning