{"total":44,"rows":[{"id":"2310.18340","title":"UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web","created":"2023-10-22","cited_by_count":78,"area":null},{"id":"2111.00970","title":"Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags","created":"2021-11-01","cited_by_count":23,"area":null},{"id":"2302.13094","title":"Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction","created":"2023-02-25","cited_by_count":23,"area":null},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2310.00583","title":"City Foundation Models for Learning General Purpose Representations from OpenStreetMap","created":"2023-10-01","cited_by_count":21,"area":null},{"id":"2403.16831","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2407.09523","title":"MuseCL: Predicting Urban Socioeconomic Indicators via Multi-Semantic Contrastive Learning","created":"2024-06-23","cited_by_count":17,"area":null},{"id":"2408.12116","title":"Geolocation Representation from Large Language Models are Generic Enhancers for Spatio-Temporal Learning","created":"2024-08-22","cited_by_count":15,"area":null},{"id":"2411.18428","title":"MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version","created":"2024-11-27","cited_by_count":14,"area":null},{"id":"2312.09681","title":"Urban Region Embedding via Multi-View Contrastive Prediction","created":"2023-12-15","cited_by_count":13,"area":null},{"id":"2503.09128","title":"FlexiReg: Flexible Urban Region Representation Learning","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2312.04606","title":"Urban Region Representation Learning with Attentive Fusion","created":"2023-12-07","cited_by_count":12,"area":null},{"id":"2109.12042","title":"Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance","created":"2021-09-24","cited_by_count":10,"area":null},{"id":"2105.02489","title":"Learning Neighborhood Representation from Multi-Modal Multi-Graph: Image, Text, Mobility Graph and Beyond","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2408.12133","title":"Self-Supervised Representation Learning for Geospatial Objects: A Survey","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2401.01107","title":"CityPulse: Fine-Grained Assessment of Urban Change with Street View Time Series","created":"2024-01-02","cited_by_count":8,"area":null},{"id":"2202.09021","title":"Effective Urban Region Representation Learning Using Heterogeneous Urban Graph Attention Network (HUGAT)","created":"2022-02-18","cited_by_count":5,"area":null},{"id":"2405.14135","title":"Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2410.02086","title":"Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2507.13385","title":"Using Multiple Input Modalities Can Improve Data-Efficiency and O.O.D. Generalization for ML with Satellite Imagery","created":"2025-07-15","cited_by_count":5,"area":null},{"id":"2605.26036","title":"CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities","created":"2026-05-25","cited_by_count":5,"area":null},{"id":"2104.12852","title":"Geographic ratemaking with spatial embeddings","created":"2021-04-26","cited_by_count":3,"area":null},{"id":"2301.01842","title":"Detecting Neighborhood Gentrification at Scale via Street-level Visual Data","created":"2023-01-04","cited_by_count":3,"area":null},{"id":"2306.04021","title":"Energy-Based Models for Cross-Modal Localization using Convolutional Transformers","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2501.07157","title":"CureGraph: Contrastive Multi-Modal Graph Representation Learning for Urban Living Circle Health Profiling and Prediction","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2510.16555","title":"Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2110.12371","title":"Neural Embeddings of Urban Big Data Reveal Emergent Structures in Cities","created":"2021-10-24","cited_by_count":2,"area":null},{"id":"2311.09240","title":"Devil in the Landscapes: Inferring Epidemic Exposure Risks from Street View Imagery","created":"2023-11-09","cited_by_count":2,"area":null},{"id":"2401.15118","title":"GeoDecoder: Empowering Multimodal Map Understanding","created":"2024-01-26","cited_by_count":2,"area":null},{"id":"2309.11354","title":"Self-supervised learning unveils change in urban housing from street-level images","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2406.04029","title":"Pre-trained Transformer Uncovers Meaningful Patterns in Human Mobility Data","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2602.15750","title":"UrbanVerse: Learning Urban Region Representation Across Cities and Tasks","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2201.12693","title":"Extracting Built Environment Features for Planning Research with Computer Vision: A Review and Discussion of State-of-the-Art Approaches","created":"2022-01-30","cited_by_count":0,"area":null},{"id":"2307.03212","title":"Attentive Graph Enhanced Region Representation Learning","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2502.04638","title":"Learning Street View Representations with Spatiotemporal Contrast","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2506.05016","title":"Multi-Point Proximity Encoding For Vector-Mode Geospatial Machine Learning","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2601.11610","title":"Multifaceted Scenario-Aware Hypergraph Learning for Next POI Recommendation","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2602.01610","title":"ToPT: Task-Oriented Prompt Tuning for Urban Region Representation Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2608.18546","title":"MARCUS: Missing-Aware Region Representation with Contextual Urban Signals for Rent Prediction","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.30964","title":"Vision Models Predict Urban Scene Appraisal with Limited Neural Alignment","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22117","title":"LE4Mob: Towards Inductive, Distance-Aware and General-Purpose Location Embedding for Human Mobility Modelling","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.22121","title":"Modelling daily activity patterns from mobile phone location data via deep representation learning","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2610.13390","title":"PlacePulse: Learning Transferable Place Representations from Structural Geographic Data","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17190","title":"CartoVec: General-Purpose Location Embeddings from Open Map Data","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}