AI Paper Atlas

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

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add multi-modal transformer with cross-modal contrastive losses (ablation)TIGeR base model · TIGeR-test-86k + CVT-test averagegeo-location error (km): 668.97 -> 238.58Improved
add multi-modal transformer with cross-modal contrastive losses (ablation)TIGeR base model · TIGeR-test-86k + CVT-test averagemonth error: 76.77 -> 57.58Improved
add classification heads as auxiliary supervision (ablation)TIGeR · TIGeR-test-86k + CVT-test averagegeo-location error (km): 238.58 -> 234.53Improved
add entropy-adaptive reranking at test time (ablation)TIGeR · TIGeR-test-86k + CVT-test averagegeo-location error (km): 234.53 -> 203.93Improved
add entropy-adaptive reranking at test time (ablation)TIGeR · TIGeR-test-86k + CVT-test averagemonth error: 57.20 -> 57.20No clear effect
provide geo-location as auxiliary input for time predictionTIGeR · CVT-testtime-of-year error: 62.88 -> 47.00Improved
provide target time as auxiliary input for geo-localizationTIGeR · TIGeR-test-86kaccuracy @200 km (%): 48.63 -> 48.34 (TIGeR-test-86k); 51.90 -> 53.40 (CVT)Mixed
TIGeR vs GT-Loc on CVT geo-time retrievalTIGeR · CVT geo-time retrievalR@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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy