Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Goodge, Adam, Ng, Wee Siong, Hooi, Bryan, Ng, See Kiong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917915977056256
author Goodge, Adam
Ng, Wee Siong
Hooi, Bryan
Ng, See Kiong
author_facet Goodge, Adam
Ng, Wee Siong
Hooi, Bryan
Ng, See Kiong
contents Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and language tasks. However, despite the prevalence of spatio-temporal data in critical domains such as transportation, public health, and environmental monitoring, spatio-temporal foundation models (STFMs) have not yet achieved comparable success. In this paper, we articulate a vision for the future of STFMs, outlining their essential characteristics and the generalization capabilities necessary for broad applicability. We critically assess the current state of research, identifying gaps relative to these ideal traits, and highlight key challenges that impede their progress. Finally, we explore potential opportunities and directions to advance research towards the aim of effective and broadly applicable STFMs.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09045
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
Goodge, Adam
Ng, Wee Siong
Hooi, Bryan
Ng, See Kiong
Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and language tasks. However, despite the prevalence of spatio-temporal data in critical domains such as transportation, public health, and environmental monitoring, spatio-temporal foundation models (STFMs) have not yet achieved comparable success. In this paper, we articulate a vision for the future of STFMs, outlining their essential characteristics and the generalization capabilities necessary for broad applicability. We critically assess the current state of research, identifying gaps relative to these ideal traits, and highlight key challenges that impede their progress. Finally, we explore potential opportunities and directions to advance research towards the aim of effective and broadly applicable STFMs.
title Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2501.09045