# CoST: Semantic-Aware Urban Understanding via Spatial-Temporal Alignment

arXiv: https://arxiv.org/abs/2608.21041 · HTML: https://mlsanity.com/paper/2608.21041/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](https://mlsanity.com/paper/1902.06148/) (2019)
- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications](https://mlsanity.com/paper/2412.02732/) (2024)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2403.05419/) (2024)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook](https://mlsanity.com/paper/2402.19348/) (2024)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining](https://mlsanity.com/paper/2405.20462/) (2024)
- [Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction](https://mlsanity.com/paper/2302.13094/) (2023)
- [UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction](https://mlsanity.com/paper/2403.16831/) (2024)
- [Multi-Label Self-Supervised Learning with Scene Images](https://mlsanity.com/paper/2308.03286/) (2023)
- [MuseCL: Predicting Urban Socioeconomic Indicators via Multi-Semantic Contrastive Learning](https://mlsanity.com/paper/2407.09523/) (2024)
- [Lightweight and Robust Representation of Economic Scales from Satellite Imagery](https://mlsanity.com/paper/1912.08197/) (2019)
- [FlexiReg: Flexible Urban Region Representation Learning](https://mlsanity.com/paper/2503.09128/) (2025)
- [UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation](https://mlsanity.com/paper/2404.14241/) (2024)
- [Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs](https://mlsanity.com/paper/2405.14135/) (2024)
- [Demo2Vec: Learning Region Embedding with Demographic Information](https://mlsanity.com/paper/2409.16837/) (2024)
- [UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations](https://mlsanity.com/paper/2510.13774/) (2025)
- [Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence](https://mlsanity.com/paper/2510.16555/) (2025)
- [Urban In-Context Learning: Bridging Pretraining and Inference through Masked Diffusion for Urban Profiling](https://mlsanity.com/paper/2508.03042/) (2025)
- [Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web](https://mlsanity.com/paper/2602.10502/) (2026)

## Built on by (most cited first, 1 of 1)

- [Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization](https://mlsanity.com/paper/2608.29880/) (2026)

## Abstract (arXiv)

Geospatial representation learning from satellite imagery is a fundamental problem for large-scale urban analysis and real-world applications. Despite recent advances, current methods struggle with cross-region generalization and semantic interpretability due to their reliance on region-specific auxiliary data and the neglect of semantic alignment within multi-temporal urban imagery. Therefore, we present CoST, a novel underlineContrastive-based underlineSpatial-underlineTemporal framework that aligns spatial context with multi-temporal semantics to extract universal geographic regularities shared across regions. Specifically, CoST explicitly models spatial correlations to capture transferable geographic structures and exploits multi-year urban change semantics to align learned representations with high-level geo-semantics. Extensive experiments demonstrate that CoST consistently achieves superior performance across various downstream tasks and in unseen scenario, yielding an average relative gain of 8.7% over the strongest competing methods across eight city-indicator settings. The code is available in hrefhttps://github.com/Arandinglv/CoSTthis repo.