Enriching Location Representation with Detailed Semantic Information

TL;DR

This paper introduces CaLLiPer+ which enhances urban spatial representations by integrating POI names and categorical labels through multimodal contrastive learning, improving land use classification, socioeconomic mapping, and location retrieval.

Contribution

It presents CaLLiPer+ as a novel extension that systematically incorporates detailed semantic information into spatial embeddings using multimodal contrastive learning.

Findings

Achieves 4-11% performance improvements on downstream tasks.

Enhances location retrieval accuracy with semantic integration.

Demonstrates the effectiveness of pretrained text encoders in spatial models.

Abstract

Spatial representations that capture both structural and semantic characteristics of urban environments are essential for urban modeling. Traditional spatial embeddings often prioritize spatial proximity while underutilizing fine-grained contextual information from places. To address this limitation, we introduce CaLLiPer+, an extension of the CaLLiPer model that systematically integrates Point-of-Interest (POI) names alongside categorical labels within a multimodal contrastive learning framework. We evaluate its effectiveness on two downstream tasks, land use classification and socioeconomic status distribution mapping, demonstrating consistent performance gains of 4% to 11% over baseline methods. Additionally, we show that incorporating POI names enhances location retrieval, enabling models to capture complex urban concepts with greater precision. Ablation studies further reveal the complementary role of POI names and the advantages of leveraging pretrained text encoders for spatial representations. Overall, our findings highlight the potential of integrating fine-grained semantic attributes and multimodal learning techniques to advance the development of urban foundation models.