Skip to main content

Search

Show all results for

Home

Person

Li Mi

About
Privacy
Disclaimer

Copyright © 2025 EPFL, all rights reserved

Graph Chatbot

Official source

https://people.epfl.ch/li.mi

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (7)

Please note that this is not a complete list of this person’s publications. It includes only semantically relevant works. For a full list, please refer to Infoscience.

Knowledge-Aware Text–Image Retrieval for Remote Sensing Images

Devis Tuia, Li Mi, Javiera Francisca Castillo Navarro

Image-based retrieval in large Earth observation archives is challenging because one needs to navigate across thousands of candidate matches only with the query image as a guide. By using text as information supporting the visual query, the retrieval syste ...

Institute of Electrical and Electronics Engineers (IEEE)2024

ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations

Devis Tuia, Antoine Bosselut, Li Mi, Syrielle Mathilde Marie Montariol, Javiera Francisca Castillo Navarro

Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with varying orientat ...

Springer Cham2024

Related units (2)

Environmental Computational Science and Earth Observation Laboratory

EPFL
ENAC
IIE
ECEO

Natural Language Processing Lab

EPFL
IC
IINFCOM
NLP

Unsupervised Multi-view UAV Image Geo-localization via Iterative Rendering

Li Mi

Unmanned Aerial Vehicle (UAV) Cross-View Geo-Localization (CVGL) poses significant challenges due to the substantial view discrepancies between oblique UAV images and overhead satellite images. Existing methods heavily rely on supervised learning with labe ...

2025