AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

LaVPR: Benchmarking Language and Vision for Place Recognition

Ofer Idan, Dan Badur, yosi keller, Yoli Shavit

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 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 learned projection (LLP) to ADS fusion (ablation)MixVPR + BGE-L ADS · AmstertimeR@1: 36.1 -> 38.1Improved
add LLP to CAT fusion (ablation)MixVPR + BGE-L CAT · AmstertimeR@1: 37.0 -> 30.2Hurt
add text descriptions via CAT fusionMixVPR · AmstertimeR@1: 35.7 -> 37.0Improved
add text descriptions via CAT fusionMixVPR · MSLS-valR@1: 83.2 -> 81.9Hurt
add language (ADS+LLP) on blurred queriesMixVPR · MSLS-BlurR@1: 70.9 -> 81.4Improved
add language (ADS+LLP) on weather queriesSALAD · MSLS-WeatherR@1: 90.7 -> 94.2Improved
add language to SSL DINOv2 backboneSALAD / CricaVPR · Relative R@1 gainR@1: <7%Mixed
add language to supervised VGG NetVLADNetVLAD · Relative R@1 gainR@1: 200%Improved
use joint fusion instead of sequential re-ranking (ablation)MixVPR + BGE · AmstertimeR@1: 1.2 -> 37.0Improved
add language to small ViT-S backboneCricaVPR-Small · MSLS-BlurR@1: 89.5 -> 93.0Improved
use LoRA instead of full fine-tuning (ablation)BLIP with MS loss · Amstertime cross-modalR@1: 0.1 -> 12.8Improved
use MS loss instead of contrastive loss (ablation)BLIP LoRA all linear r=64 · Amstertime cross-modalR@1: 0.1 -> 12.8Improved

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