arXiv subjects

Namwoo Kim

Publications and source records attributed to Namwoo Kim.

10 recordsLinked to original sources

arXiv2026

Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding

Urban region embeddings have shown promising results in diverse urban sensing tasks such as crime, income, and service-call prediction. Recent methods improve representation quality by integrating mobility data with auxiliary modalities, using cross-view attention or contrastive objectives to align heterogeneous features into a unified region representation. However, leveraging the temporal dynamics of human mobility remains under-explored. Regional inflow and outflow fluctuate throughout the day, and inter-region connections emerge, persist, and dissolve over time. Moreover, prevailing fusion strategies combine views additively and miss the joint signal that emerges only when views co-occur. To address these gaps, we propose Mobility Stream-Structure Synergy (MoSS), which derives complementary views from mobility data: a Sequence view that preserves each region's hourly inflow/outflow profile, and a Structure view based on zigzag persistence diagrams that capture how regional connectivity emerges, persists, and dissolves over time. A synergy module then extracts emergent representations from the co-occurrence of these views through multi-degree interactions, explicitly capturing higher-order signal across views. Extensive experiments on New York City and Chicago show that MoSS achieves state-of-the-art performance across three downstream tasks using mobility data alone, outperforming baselines that rely on auxiliary modalities.

cs.LG↗

arXiv2026

HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting

Multi-scale modeling has become an effective approach for long-term time series forecasting, capturing temporal patterns that range from fine-grained local dynamics to coarse global trends. Representations across these temporal scales are inherently hierarchical, with coarser scales abstracting and aggregating information from finer ones. While existing approaches readily exchange information across these scales, the hierarchy itself is typically left as an emergent byproduct of such interactions rather than captured as a geometric structure in its own right. In this paper, we introduce HypLTSF, a framework that endows the multi-scale hierarchy with a concrete geometric form by embedding scale-wise representations into the Poincar\'e ball, whose exponentially expanding volume naturally accommodates hierarchical structures. To align this geometry with the temporal hierarchy, HypLTSF imposes two constraints: (1) a radial constraint that orders embeddings by their level of abstraction, and (2) an angular constraint that groups fine-scale patterns sharing a common coarser-scale ancestor. Extensive experiments on long-term time series forecasting benchmarks show that HypLTSF achieves state-of-the-art performance, suggesting that explicitly modeling the multi-scale hierarchy as a geometric structure is effective for forecasting.

cs.LG↗

arXiv2025

How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Images

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban domain remains underexplored. To address this gap, we conduct a comparative study of three off-the-shelf VLMs-BLIP-2, InstructBLIP, and LLaVA-1.5-evaluating both zero-shot performance and the effects of fine-tuning with a synthetic VQA dataset specific to urban scenes. We construct such dataset from segmentation, depth, and object detection predictions of street-view images, pairing each question with LLM-generated Chain-of-Thought (CoT) answers for step-by-step reasoning supervision. Results show that while VLMs perform reasonably well in zero-shot settings, fine-tuning with our synthetic CoT-supervised dataset substantially boosts performance, especially for challenging question types such as negation and counterfactuals. This study introduces urban spatial reasoning as a new challenge for VLMs and demonstrates synthetic dataset construction as a practical path for adapting general-purpose models to specialized domains.

cs.CV↗

arXiv2025

USE-LFA: A Data-Driven Framework for UAM Site Evaluation using Latent Factor Analysis

Urban air mobility (UAM) introduces new challenges for infrastructure planning, requiring data driven approaches for sustainable site selection. This study proposes USE-LFA (Urban Site Evaluation using Latent Factor Analysis), a framework designed to support equitable and environmentally conscious siting of urban ports. Applying latent factor analysis to 25 urban attributes in Seoul, the framework identifies six latent factors, grouped into two dimensions: Suitability and Attractiveness. These dimensions are combined through a tunable prioritization metric, enabling alignment with local strategic goals. The analysis uncovers spatial typologies and clustered siting patterns, highlighting regional disparities in site potential. Sensitivity analysis demonstrates that small adjustments in the Suitability Attractiveness weighting substantially affect viable site candidates, emphasizing the need for calibrated decision-making. USE-LFA facilitates interpretable and transferable analysis across different urban contexts and datasets, offering a scalable approach to integrating UAM and other emerging mobility systems into urban environments, while advancing sustainable and inclusive transport infrastructure development.

stat.AP↗

arXiv2025

MobiCLR: Mobility Time Series Contrastive Learning for Urban Region Representations

Recently, learning effective representations of urban regions has gained significant attention as a key approach to understanding urban dynamics and advancing smarter cities. Existing approaches have demonstrated the potential of leveraging mobility data to generate latent representations, providing valuable insights into the intrinsic characteristics of urban areas. However, incorporating the temporal dynamics and detailed semantics inherent in human mobility patterns remains underexplored. To address this gap, we propose a novel urban region representation learning model, Mobility Time Series Contrastive Learning for Urban Region Representations (MobiCLR), designed to capture semantically meaningful embeddings from inflow and outflow mobility patterns. MobiCLR uses contrastive learning to enhance the discriminative power of its representations, applying an instance-wise contrastive loss to capture distinct flow-specific characteristics. Additionally, we develop a regularizer to align output features with these flow-specific representations, enabling a more comprehensive understanding of mobility dynamics. To validate our model, we conduct extensive experiments in Chicago, New York, and Washington, D.C. to predict income, educational attainment, and social vulnerability. The results demonstrate that our model outperforms state-of-the-art models.

cs.LG↗

arXiv2025

TopoCL: Topological Contrastive Learning for Time Series

Universal time series representation learning is challenging but valuable in real-world applications such as classification, anomaly detection, and forecasting. Recently, contrastive learning (CL) has been actively explored to tackle time series representation. However, a key challenge is that the data augmentation process in CL can distort seasonal patterns or temporal dependencies, inevitably leading to a loss of semantic information. To address this challenge, we propose Topological Contrastive Learning for time series (TopoCL). TopoCL mitigates such information loss by incorporating persistent homology, which captures the topological characteristics of data that remain invariant under transformations. In this paper, we treat the temporal and topological properties of time series data as distinct modalities. Specifically, we compute persistent homology to construct topological features of time series data, representing them in persistence diagrams. We then design a neural network to encode these persistent diagrams. Our approach jointly optimizes CL within the time modality and time-topology correspondence, promoting a comprehensive understanding of both temporal semantics and topological properties of time series. We conduct extensive experiments on four downstream tasks-classification, anomaly detection, forecasting, and transfer learning. The results demonstrate that TopoCL achieves state-of-the-art performance.

cs.LG↗

arXiv2022

Effective Urban Region Representation Learning Using Heterogeneous Urban Graph Attention Network (HUGAT)

Revealing the hidden patterns shaping the urban environment is essential to understand its dynamics and to make cities smarter. Recent studies have demonstrated that learning the representations of urban regions can be an effective strategy to uncover the intrinsic characteristics of urban areas. However, existing studies lack in incorporating diversity in urban data sources. In this work, we propose heterogeneous urban graph attention network (HUGAT), which incorporates heterogeneity of diverse urban datasets. In HUGAT, heterogeneous urban graph (HUG) incorporates both the geo-spatial and temporal people movement variations in a single graph structure. Given a HUG, a set of meta-paths are designed to capture the rich urban semantics as composite relations between nodes. Region embedding is carried out using heterogeneous graph attention network (HAN). HUGAT is designed to consider multiple learning objectives of city's geo-spatial and mobility variations simultaneously. In our extensive experiments on NYC data, HUGAT outperformed all the state-of-the-art models. Moreover, it demonstrated a robust generalization capability across the various prediction tasks of crime, average personal income, and bike flow as well as the spatial clustering task.

cs.LG↗

arXiv2020

The effect of adaptive mobility policy to the spread of COVID-19 in urban environment: intervention analysis of Seoul, South Korea

Although severe mobility restrictions are recognized as the key enabler to contain COVID-19, there has been few scientific studies to validate such approach, especially in urban context. This study analyzes mobility pattern changes in Seoul, South Korea that adopted adaptive approach toward mobility. Intervention analyses reveal that major mobility reduction did occur two weeks before the city's case peak. Such voluntary adjustments exhibit strong preference shift toward private mode from public transit. Large reductions occurred in non-essential and high-contact activities of shopping and dining, while work and Starbucks trips were less affected. The collective evaluation reveal that major changes in epidemiology, mobility and policy occurred simultaneously, with no lagging nor leading contributors. Our study demonstrates that collective understanding the mutual aspects among mobility, epidemiology and policy is essential. Incremental and flexible mobility restriction is not only possible but necessary, especially for a pandemic of extensive spatial and temporal scales.

physics.soc-ph↗

arXiv2020

Running the COVID-19 marathon: the behavioral adaptations in mobility and facemask over 27 weeks of pandemic in Seoul, South Korea

Battle with COVID-19 turned out to be a marathon, not a sprint, and behavioral adjustments have been unavoidable to stay viable. In this paper, we employ a data-centric approach to investigate individual mobility adaptations and mask-wearing in Seoul, South Korea. We first identify six epidemic phases and two waves based on COVID-19 case count and its geospatial dispersion. The phase-specific linear models reveal the strong, self-driven mobility reductions in the first escalation and peak with a common focus on public transit use and less-essential weekend/afternoon trips. However, comparable reduction was not present in the second wave, as the shifted focus from mobility to mask-wearing was evident. Although no lockdowns and gentle nudge to wear mask seemed counter-intuitive, simple and persistent communication on personal safety has been effective and sustainable to induce cooperative behavioral adaptations. Our phase-specific analyses and interpretation highlight the importance of targeted response consistent with the fluctuating epidemic risk.

cs.CY↗

arXiv2020

COVID-19 Mobility Data Collection of Seoul, South Korea

The relationship between pandemic and human mobility has received considerable attention from scholars, as it can provide an indication of how mobility patterns change in response to a public health crisis or whether reduced mobility contributes to preventing the spread of an infectious disease. While several studies attempted to unveil such relationship, no studies have focused on changes in human mobility at a finer scale utilizing comprehensive, high-resolution data. To address the complex association between pandemic's spread and human mobility, this paper presents two categories of mobility datasets - trip mode and trip purpose - that concern nearly 10 million citizens' movements during COVID-19 in the capital city of South Korea, Seoul, where no lockdowns has been imposed. We curate hourly data of subway ridership, traffic volume and population present count at selected points of interests. The results to be derived from the presented datasets can be used as an important reference for public health decision making in the post COVID-19 era.

cs.CY↗