论文名称: GeoChat: Grounded Large Vision-Language Model for Remote Sensing 模型架构: MLLM Visual Encoder: Transformer Text Encoder: Transformer Model Details: Vision Encoder：CLIP-ViTText Encoder...
论文名称: Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment 模型架构: VLM Visual Encoder: Transformer Model Details: Vision Encoder：CLIP ViT-B Task...
论文名称: SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model 模型架构: MLLM Visual Encoder: Transformer Text Encoder: Transformer Model Det...
论文名称: Generic Knowledge Boosted Pre-training ForRemote Sensing Images Link: https://arxiv.org/pdf/2401.04614 Published in: IEEE Transactions on Geoscience and Remote Sensing 2024 Type: Pre...
论文名称: Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time Series Link: https://ieeexplore.ieee.org/document/10414422 Published in: JSTARS 2024 Type: Pretrain ...
论文名称: On the Foundations of Earth and Climate Foundation Models Published in: Arxiv 2024 Type: Other 备注: 针对地球和气候科学 Short Summary: 有一些问题：1. 专注于预训练数据集的策划，往往过度采样城市等人口稠密地区，而在雨林、极地和海洋等人口稀少地区采...
论文名称: GeoLLM: Extracting Geospatial Knowledge from Large Language Models 模型架构: Other Model Details: RoBERTa、LLaMA-2、GPT-3.5 Link: https://arxiv.org/abs/2310.06213 Code/Project: https://g...
论文名称: MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning Published in: Arxiv 2024 Type: Other 备注: 多预文本遮罩自编码器，解码器包括重建和一些下游任务 Backbone: ConvNext
数据集名称: Constellation 任务: 遥感图像目标检测 高海拔下的目标检测 发布时间: 2024 模态: 图像 数量: 包含了从城市交通路口高海拔摄像头获取的13K图像 代码源链接: https://github.com/zk2172-columbia/constellation-dataset 论文源链接: https://arxiv.org/ab...
论文名称: Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis 模型架构: Agent Task: Change Detection, Change Caption Link: https://arxiv.org/abs/2403....