Research map / Vision-language and multimodal / Human and embodied modeling
TIGER: A Unified Framework for Time, Images and Geo-location Retrieval
David G. Shatwell, Sirnam Swetha, Mubarak Shah
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-modal transformer with cross-modal contrastive losses (ablation) | TIGeR base model · TIGeR-test-86k + CVT-test average | geo-location error (km): 668.97 -> 238.58 | Improved |
| add multi-modal transformer with cross-modal contrastive losses (ablation) | TIGeR base model · TIGeR-test-86k + CVT-test average | month error: 76.77 -> 57.58 | Improved |
| add classification heads as auxiliary supervision (ablation) | TIGeR · TIGeR-test-86k + CVT-test average | geo-location error (km): 238.58 -> 234.53 | Improved |
| add entropy-adaptive reranking at test time (ablation) | TIGeR · TIGeR-test-86k + CVT-test average | geo-location error (km): 234.53 -> 203.93 | Improved |
| add entropy-adaptive reranking at test time (ablation) | TIGeR · TIGeR-test-86k + CVT-test average | month error: 57.20 -> 57.20 | No clear effect |
| provide geo-location as auxiliary input for time prediction | TIGeR · CVT-test | time-of-year error: 62.88 -> 47.00 | Improved |
| provide target time as auxiliary input for geo-localization | TIGeR · TIGeR-test-86k | accuracy @200 km (%): 48.63 -> 48.34 (TIGeR-test-86k); 51.90 -> 53.40 (CVT) | Mixed |
| TIGeR vs GT-Loc on CVT geo-time retrieval | TIGeR · CVT geo-time retrieval | R@1 (%): 16.45 -> 14.55 (R@1); 22.59 -> 29.98 (R@10) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GT-Loc — GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space (ICCV 2025) · better on 3 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models (NeurIPS 2024 · similarity 0.85)
- GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization (NeurIPS 2025 · similarity 0.85)
- TimeSpot: Benchmarking Geo-Temporal Understanding in Vision–Language Models in Real-World Settings (ICML 2026 · similarity 0.84)
- Re-thinking Temporal Search for Long-Form Video Understanding (CVPR 2025 · similarity 0.84)
- OpenStreetView-5M: The Many Roads to Global Visual Geolocation (CVPR 2024 · similarity 0.84)
- Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
