AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Where We Are and What We're Looking At: Query Based Worldwide Image Geo-Localization Using Hierarchies and Scenes

Brandon Clark, Alec Kerrigan, Parth Parag Kulkarni, Vicente Vivanco Cepeda, Mubarak Shah

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 18 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
Hierarchy-dependent scene-query decoder (scene queries with max-confidence selection) vs. no scene prediction (ablation)Swin-based GeoDecoder · Im2GPS3kaccuracy @ 1 km: +1.1 (11.7 to 12.8)Improved
Scene-query selection vs. scene prediction as a secondary task (ablation)Swin-based GeoDecoder · YFCC26kaccuracy @ 1 km: +0.4 (9.7 to 10.1)Improved
Replace Swin encoder with ViT encoder in the full model (ablation)GeoDecoder · YFCC26kaccuracy @ 1 km: -1.4 (10.1 to 8.7)Hurt
Use 2 hierarchy-dependent decoder layers vs. 0 (fully hierarchy-independent) (ablation)GeoDecoder · Im2GPS3kaccuracy @ 1 km: +0.6 (12.2 to 12.8)Improved
Use 2 hierarchy-dependent decoder layers vs. 0 (ablation)GeoDecoder · YFCC26kaccuracy @ 1 km: +0.4 (9.7 to 10.1)Improved
Increase hierarchy-dependent layers from 2 to 6 (ablation)GeoDecoder · YFCC26kaccuracy @ 1 km: -1.4 (10.1 to 8.7)Hurt
GeoDecoder depth 3 to 8 layers (ablation)GeoDecoder · Im2GPS3kaccuracy @ 1 km: +0.9 (11.9 to 12.8)Improved
GeoDecoder depth 8 to 10 layers (ablation)GeoDecoder · Im2GPS3kaccuracy @ 1 km: -0.3 (12.8 to 12.5)Hurt
Train with 7 geographic hierarchies vs. 1 (ablation)GeoDecoder · Im2GPS3kaccuracy @ 1 km: +4.5 (9.8 to 14.3)Improved
Train with 7 hierarchies vs. 3 hierarchies (ablation)GeoDecoder · GWS15kaccuracy @ 1 km: 0.2 vs 0.2 at 1 km; 1 km +0.4 at 5 hierarchiesMixed
Use 16 scene labels instead of 365 (ablation)GeoDecoder · YFCC26kaccuracy @ 1 km: +0.2 (8.5 to 8.7)Improved
Proposed hierarchical scene-query geo-decoder vs. prior SOTA TranslocatorSwin-based GeoDecoder · YFCC26kaccuracy @ 1 km: +2.9 (7.2 to 10.1)Improved

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