SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
K-STEMIT reduces RMSE by 21% for subsurface stratigraphy thickness estimation from radar data via a knowledge-informed spatio-temporal GNN with adaptive feature fusion and physical priors from the MAR weather model.
Lightweight multimodal projector alignment transfers RGB VLMs to thermal drone imagery, achieving F1 scores of 0.915-0.968 for deer, rhino, and elephant recognition plus high enumeration accuracy and habitat context interpretation on a real drone dataset.
Earth embeddings from satellite images predict neighborhood-level urban indicators with higher accuracy for built-environment outcomes than for behavior-driven ones, showing city-specific variation but year-to-year stability.
MeCSAFNet reports mIoU gains of 4.8-19.6% over U-Net and SegFormer baselines on FBP and Potsdam datasets by processing spectral channels separately and fusing features with CBAM attention.
citing papers explorer
-
SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining
SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.
-
K-STEMIT: Knowledge-Informed Spatio-Temporal Efficient Multi-Branch Graph Neural Network for Subsurface Stratigraphy Thickness Estimation from Radar Data
K-STEMIT reduces RMSE by 21% for subsurface stratigraphy thickness estimation from radar data via a knowledge-informed spatio-temporal GNN with adaptive feature fusion and physical priors from the MAR weather model.
-
Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
Lightweight multimodal projector alignment transfers RGB VLMs to thermal drone imagery, achieving F1 scores of 0.915-0.968 for deer, rhino, and elephant recognition plus high enumeration accuracy and habitat context interpretation on a real drone dataset.
-
Earth Embeddings Reveal Diverse Urban Signals from Space
Earth embeddings from satellite images predict neighborhood-level urban indicators with higher accuracy for built-environment outcomes than for behavior-driven ones, showing city-specific variation but year-to-year stability.
-
Multi-encoder ConvNeXt Network with Smooth Attentional Feature Fusion for Multispectral Semantic Segmentation
MeCSAFNet reports mIoU gains of 4.8-19.6% over U-Net and SegFormer baselines on FBP and Potsdam datasets by processing spectral channels separately and fusing features with CBAM attention.