TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918520638406656 |
|---|---|
| author | Wasi, Azmine Toushik Ridoy, Shahriyar Zaman Tonmoy, Koushik Ahamed Tshering, Kinga Hasan, S. M. Muhtasimul Faisal, Wahid Mohiuddin, Tasnim Parvez, Md Rizwan |
| author_facet | Wasi, Azmine Toushik Ridoy, Shahriyar Zaman Tonmoy, Koushik Ahamed Tshering, Kinga Hasan, S. M. Muhtasimul Faisal, Wahid Mohiuddin, Tasnim Parvez, Md Rizwan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06687 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings Wasi, Azmine Toushik Ridoy, Shahriyar Zaman Tonmoy, Koushik Ahamed Tshering, Kinga Hasan, S. M. Muhtasimul Faisal, Wahid Mohiuddin, Tasnim Parvez, Md Rizwan Computer Vision and Pattern Recognition Computation and Language Emerging Technologies Multimedia Robotics 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. |
| title | TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings |
| topic | Computer Vision and Pattern Recognition Computation and Language Emerging Technologies Multimedia Robotics |
| url | https://arxiv.org/abs/2603.06687 |