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

• URL: http://arxiv.org/abs/2603.06687v1
• Date: Wed, 04 Mar 2026 07:27:35 GMT
• Title: TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings
• Abstract summary: We introduce TimeSpot, a benchmark for evaluating real-world geo-temporal reasoning in vision-language models.<n>TimeSpot comprises 1,455 ground-level images from 80 countries.<n>It requires structured prediction of temporal attributes and geographic attributes directly from visual evidence.<n>It also includes spatial-temporal reasoning tasks that test physical plausibility under real-world uncertainty.
• Score: 10.091610297997613
• License: http://creativecommons.org/licenses/by/4.0/
• 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: https://TimeSpot-GT.github.io.

Related papers

• Recovering Temporal and Geographic Signals from Language Model Embeddings [0.0]
  We study whether language-model embeddings encode structured real-world information.<n>We use a projection-based method that operates directly on output embeddings.<n>We find that embedding projections recover meaningful chronological and spatial structure.
  arXiv  Detail & Related papers  (2026-09-04T21:03:06Z)
• GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation [1.7370190083648793]
  Modern Vision-Language Models (VLMs) perform well above the human baseline in image geolocalization.<n>We introduce textbfGeoAgent, an agentic environment-based benchmark that requires agents to navigate Street View environments.<n>Our analysis shows that modern VLMs struggle to discern regional patterns while succeeding at country- and continent-level predictions.
  arXiv  Detail & Related papers  (2026-08-30T00:19:49Z)
• Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization [3.713195826948382]
  Vision-Language Models (VLMs) have demonstrated strong zero-shot reasoning capabilities across multimodal tasks.<n>We present a systematic evaluation of multiple state-of-the-art VLMs for country-level image geolocalization using ground-view imagery only.
  arXiv  Detail & Related papers  (2026-04-17T17:09:14Z)
• Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning [72.13218601075958]
  We introduce textbfWanderBench, the first open access global geolocation benchmark for actionable geolocation reasoning in embodied scenarios.<n>We propose textbfGeoAoT (Action of Thought), a underlineGeolocation framework with underlineAction of underlineThough, which couples reasoning with embodied actions.<n>Experiments on 19 large multimodal models show that GeoAoT achieves superior fine-grained localization and stronger generalization in dynamic environments.
  arXiv  Detail & Related papers  (2026-03-11T06:24:10Z)
• GTPred: Benchmarking MLLMs for Interpretable Geo-localization and Time-of-capture Prediction [21.94131531384186]
  We introduce GTPred, a novel benchmark for geo-temporal prediction.<n>We evaluate MLLM predictions by jointly considering year and hierarchical location sequence matching.<n>Results also demonstrate that incorporating temporal information significantly enhances location inference performance.
  arXiv  Detail & Related papers  (2026-01-19T16:34:25Z)
• GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization [70.65458151146767]
  Cross-view localization is crucial for large-scale outdoor applications like autonomous navigation and augmented reality.<n>Existing methods often rely on fully supervised learning, which requires costly ground-truth pose annotations.<n>We propose GeoDistill, a framework that uses teacher-student learning with Field-of-View (FoV)-based masking.
  arXiv  Detail & Related papers  (2025-07-15T03:00:15Z)
• GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space [48.09196906704634]
  GT-Loc is a novel retrieval-based method that jointly predicts the capture time (hour and month) and geo-location (GPS coordinates) of an image.<n>Our approach employs separate encoders for images, time, and location, aligning their embeddings within a shared high-dimensional feature space.
  arXiv  Detail & Related papers  (2025-07-14T16:54:57Z)
• Around the World in 24 Hours: Probing LLM Knowledge of Time and Place [18.17538075862074]
  We present the first evaluation of the ability of language models to jointly reason over time and space.<n>We evaluate eight open chat models of three different model families for different combinations of temporal and geographic knowledge.<n>We do not find clear correlations of performance with specific geographic regions.
  arXiv  Detail & Related papers  (2025-06-04T14:14:28Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization [61.10806364001535]
  Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. Existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. We propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
  arXiv  Detail & Related papers  (2023-09-27T20:54:56Z)
• GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark [56.08664336835741]
  We propose a GeoGraphic Language Understanding Evaluation benchmark, named GeoGLUE. We collect data from open-released geographic resources and introduce six natural language understanding tasks. We pro vide evaluation experiments and analysis of general baselines, indicating the effectiveness and significance of the GeoGLUE benchmark.
  arXiv  Detail & Related papers  (2023-05-11T03:21:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.