HM-Bench is the first benchmark for MLLMs on hyperspectral images, showing models struggle with complex spatial-spectral reasoning and perform better with visual PCA images than textual reports.
Available: https://arxiv.org/abs/2410.19552
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5roles
background 1polarities
background 1representative citing papers
Earth-OneVision is a unified 2B-parameter RS-MLLM supporting six modalities and nine tasks via FGVLA, SLIS, and PCMA mechanisms plus a 34M QA-pair dataset, reporting competitive or superior benchmark results versus larger models.
An iterative multi-agent feedback pipeline finds ~5× more multi-temporal news events in satellite imagery than traditional geocoding and yields a 5,000-sequence captioning dataset.
HiSem adds bidirectional differential attention and a two-level hierarchical routing module with MoE to handle semantic granularity differences in remote sensing change captioning, reporting +7.52% BLEU-4 on WHU-CDC.
ChatENV fine-tunes Qwen-2.5-VL on a 177k-image dataset of temporal satellite pairs with sensor metadata to support interactive temporal and what-if reasoning for environmental monitoring.
citing papers explorer
-
HM-Bench: A Comprehensive Benchmark for Multimodal Large Language Models in Hyperspectral Remote Sensing
HM-Bench is the first benchmark for MLLMs on hyperspectral images, showing models struggle with complex spatial-spectral reasoning and perform better with visual PCA images than textual reports.
-
Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks
Earth-OneVision is a unified 2B-parameter RS-MLLM supporting six modalities and nine tasks via FGVLA, SLIS, and PCMA mechanisms plus a 34M QA-pair dataset, reporting competitive or superior benchmark results versus larger models.
-
A Multi-Agent Feedback System for Detecting and Describing News Events in Satellite Imagery
An iterative multi-agent feedback pipeline finds ~5× more multi-temporal news events in satellite imagery than traditional geocoding and yields a 5,000-sequence captioning dataset.
-
HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
HiSem adds bidirectional differential attention and a two-level hierarchical routing module with MoE to handle semantic granularity differences in remote sensing change captioning, reporting +7.52% BLEU-4 on WHU-CDC.
-
ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation
ChatENV fine-tunes Qwen-2.5-VL on a 177k-image dataset of temporal satellite pairs with sensor metadata to support interactive temporal and what-if reasoning for environmental monitoring.