Abstract:Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications such as disaster management, traffic planning, embodied navigation, world modeling, and geography education. Although recent vision-language models (VLMs) have advanced image geo-localization using cues like landmarks and road signs, their ability to reason about temporal signals and physically grounded spatial cues remains limited. To address this gap, we introduce TimeSpot, a benchmark for evaluating real-world geo-temporal reasoning in VLMs. TimeSpot comprises 1,455 ground-level images from 80 countries and requires structured prediction of temporal attributes (season, month, time of day, daylight phase) and geographic attributes (continent, country, climate zone, environment type, latitude-longitude) directly from visual evidence. It also includes spatial-temporal reasoning tasks that test physical plausibility under real-world uncertainty. Evaluations of state-of-the-art open- and closed-source VLMs show low performance, particularly for temporal inference. While supervised fine-tuning yields improvements, results remain insufficient, highlighting the need for new methods to achieve robust, physically grounded geo-temporal understanding TimeSpot is available at: this https URL.
| Comments: | Accepted to ICML 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Emerging Technologies (cs.ET); Multimedia (cs.MM); Robotics (cs.RO) |
| Cite as: | arXiv:2603.06687 [cs.CV] |
| (or arXiv:2603.06687v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2603.06687 arXiv-issued DOI via DataCite |
From: Azmine Toushik Wasi [view email]
[v1]
Wed, 4 Mar 2026 07:27:35 UTC (12,321 KB)
[v2]
Mon, 25 May 2026 15:45:50 UTC (12,367 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。