Location Sensitive Image Retrieval And Tagging
2020 · Raul Gomez, Jaume Gibert, Lluis Gomez, et al.
Abstract
People from different parts of the globe describe objects and concepts in distinct manners. Visual appearance can thus vary across different geographic locations, which makes location a relevant contextual information when analysing visual data. In this work, we address the task of image retrieval related to a given tag conditioned on a certain location on Earth. We present LocSens, a model that learns to rank triplets of images, tags and coordinates by plausibility, and two training strategies to balance the location influence in the final ranking. LocSens learns to fuse textual and location information of multimodal queries to retrieve related images at different levels of location granularity, and successfully utilizes location information to improve image tagging.
Authors
(none)
Tags
Stats
Related papers
- Img2loc: Revisiting Image Geolocalization Using Multi-modality Foundation Models And Image-based Retrieval-augmented Generation (2024)9.23
- Leveraging Efficientnet And Contrastive Learning For Accurate Global-scale Location Estimation (2021)9.03
- Megaloc: One Retrieval To Place Them All (2025)9.19
- Location Field Descriptors: Single Image 3D Model Retrieval In The Wild (2019)11.39
- Learning To Evaluate Performance Of Multi-modal Semantic Localization (2022)10.61
- LOCORE: Image Re-ranking With Long-context Sequence Modeling (2025)2.26
- G3: An Effective And Adaptive Framework For Worldwide Geolocalization Using Large Multi-modality Models (2024)3.58
- Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11