arXiv 2603.066872026-05-25cs.CVcs.CLcs.ETcs.MMcs.RO

TimeSpot: 在真实世界场景中评估视觉语言模型的地理时间理解能力

TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings

Computational Intelligence and Operations Laboratory (CIOL), Bangladesh（计算智能与运筹实验室（CIOL），孟加拉国）；Shahjalal University of Science and Technology (SUST), Sylhet, Bangladesh（沙赫jalal科学与技术大学（SUST），沙赫里尔，孟加拉国）；North South University (NSU), Dhaka, Bangladesh（北南大学（NSU），达卡，孟加拉国）；Qatar Computing Research Institute (QCRI), Doha, Qatar（卡塔尔计算研究中心（QCRI），多哈，卡塔尔）

Azmine Toushik Wasi, Shahriyar Zaman Ridoy, Koushik Ahamed Tonmoy, Kinga Tshering, S. M. Muhtasimul Hasan, Wahid Faisal, Tasnim Mohiuddin, Md Rizwan Parvez

备注：: Accepted to ICML 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出TimeSpot基准，通过1,455张全球图像评估视觉语言模型在时间属性（季节、月份、时段、日光相位）和地理属性（大洲、国家、气候带、环境类型、经纬度）上的推理能力，发现现有模型性能低下，尤其时间推理不足。

摘要：

地理时间理解，即仅从视觉输入推断位置、时间和上下文属性的能力，支撑着灾害管理、交通规划、具身导航、世界建模和地理教育等应用。尽管最近的视觉语言模型（VLM）利用地标和路标等线索在图像地理定位方面取得了进展，但它们推理时间信号和物理基础空间线索的能力仍然有限。为弥补这一差距，我们引入了TimeSpot，一个用于评估VLM在真实世界中进行地理时间推理的基准。TimeSpot包含来自80个国家的1,455张地面图像，要求直接从视觉证据中结构化预测时间属性（季节、月份、时段、日光相位）和地理属性（大洲、国家、气候带、环境类型、经纬度）。它还包括时空推理任务，测试在真实世界不确定性下的物理合理性。对最先进的开源和闭源VLM的评估显示性能低下，尤其是时间推理。虽然监督微调带来了改进，但结果仍不充分，凸显了需要新方法来实现稳健的、基于物理的地理时间理解。TimeSpot可在 https://TimeSpot-GT.github.io 获取。

英文摘要：

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: https://TimeSpot-GT.github.io.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。