Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Zirui, Tang, Raphael, Bianco, Mike, Zhang, Qi, Madhok, Rishi, Karianakis, Nikolaos, Yu, Fuxun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.06993
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915484445704192
author Xu, Zirui
Tang, Raphael
Bianco, Mike
Zhang, Qi
Madhok, Rishi
Karianakis, Nikolaos
Yu, Fuxun
author_facet Xu, Zirui
Tang, Raphael
Bianco, Mike
Zhang, Qi
Madhok, Rishi
Karianakis, Nikolaos
Yu, Fuxun
contents EarthVision Embed2Scale challenge (CVPR 2025) aims to develop foundational geospatial models to embed SSL4EO-S12 hyperspectral geospatial data cubes into embedding vectors that faciliatetes various downstream tasks, e.g., classification, regression, etc. In this technical report, we introduce our proposed method for the Top-1 winning solution on the Embed2Scale Challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06993
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Geospatial Foundational Embedder: Top-1 Winning Solution on EarthVision Embed2Scale Challenge (CVPR 2025)
Xu, Zirui
Tang, Raphael
Bianco, Mike
Zhang, Qi
Madhok, Rishi
Karianakis, Nikolaos
Yu, Fuxun
Computer Vision and Pattern Recognition
EarthVision Embed2Scale challenge (CVPR 2025) aims to develop foundational geospatial models to embed SSL4EO-S12 hyperspectral geospatial data cubes into embedding vectors that faciliatetes various downstream tasks, e.g., classification, regression, etc. In this technical report, we introduce our proposed method for the Top-1 winning solution on the Embed2Scale Challenge.
title Geospatial Foundational Embedder: Top-1 Winning Solution on EarthVision Embed2Scale Challenge (CVPR 2025)
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06993