AI Paper Atlas

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

GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space

David G. Shatwell, Ishan Rajendrakumar Dave, Sirnam Swetha, Mubarak Shah

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 4 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
jointly train image-time and image-location alignment (GT-Loc vs image-time only TimeLoc) (ablation)GT-Loc · SkyFinder unseen camerasTPS: 75.49 -> 77.00Improved
replace regression/classification heads with retrieval-based time predictionCLIP ViT-L/14 · SkyFinder unseen camerasTPS: 74.33 (reg. head) -> 75.49 (TimeLoc) -> 77.00 (GT-Loc)Improved
use temporal metric learning with soft targets instead of CLIP-style hard-positive contrastive loss (ablation)GT-Loc · SkyFinder unseen camerasTPS: 71.12 -> 77.00Improved
use toroidal cyclic distance instead of Euclidean distance in TML (ablation)GT-Loc · SkyFinder unseen camerasTPS: 75.88 -> 77.00Improved
use CLIP ViT-L/14 backbone instead of DINOv2-L or OpenCLIP-G (ablation)TimeLoc · SkyFinderTPS: 68.71 (DINOv2-L), 74.65 (OpenCLIP-G) -> 75.49Improved
use RFF time encoder instead of Time2Vec or circular decomposition (ablation)GT-Loc · SkyFinderTPS: 75.99 (Time2Vec) -> 77.00Improved
use monthly instead of daily time-of-year scale (ablation)GT-Loc · SkyFinderTPS: 76.61 -> 77.00No clear effect
reduce training data to 5% (ablation)GT-Loc · SkyFinderTPS: 77.00 -> 72.07Hurt
add Gaussian label noise to training timestamps (ablation)GT-Loc · SkyFinderTPS: 77.00 -> 76.00 (sigma 1), 73.81 (sigma 2), 69.92 (sigma 3)Mixed
joint image-location alignment for geo-localizationGT-Loc vs GeoCLIP · Im2GPS3k 1 kmaccuracy (%): 14.11 -> 14.41Improved
use GT-Loc unified embedding for composed time+location retrievalGT-Loc · SkyFinder composed retrievalR@10: 29.46 -> 38.54Improved

Later papers that compared with this method

1 later accepted paper reports GT-Loc as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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