Changes to Captions An Attentive Network for Remote Sensing Change Captioning

论文名称: Changes to Captions: An Attentive Network for Remote Sensing Change Captioning Task: Image Caption Link: https://arxiv.org/abs/2304.01091 Code/Project: https://github.com/shizhenchan...

Apr 28, 2023 Arxiv

Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning

论文名称: Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning 模型架构: VLM Visual Encoder: Transformer Text Encoder: Transformer Model Details: Vision Encoder：CLI...

Apr 22, 2023 Arxiv

RingMo-lite A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework

论文名称: RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework Link: https://arxiv.org/abs/2309.09003 Published in: Arxiv 2023 Type: Pretrain Co...

Apr 13, 2023 Arxiv

TOV The original vision model for optical remote sensing image understanding via self-supervised learning

论文名称: TOV: The original vision model for optical remote sensing image understanding via self-supervised learning Link: https://arxiv.org/abs/2204.04716 Published in: IEEE Journal of Selected...

Apr 9, 2023 IEEE

Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing

论文名称: Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing Link: https://arxiv.org/abs/2310.18653 Published in: Arxiv 2023 Type: Pretrain Code/Project: https:...

Mar 25, 2023 Arxiv

Tree-GPT Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis

论文名称: Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis 模型架构: Agent Model Details: gpt-4 Link: https://arxiv.org/a...

Mar 22, 2023 Arxiv

RS5M

数据集名称: RS5M 任务: 遥感图文匹配发布时间: 2023 模态: 图像、文本数量: 500万张带有英文描述的遥感图像代码源链接: https://huggingface.co/datasets/Zilun/RS5M 论文源链接: https://arxiv.org/abs/2306.11300 详细描述: 图像-文本配对的数据集RS5M，其中包...

Mar 10, 2023 图文对

DeCUR decoupling common & unique representations for multimodal self-supervision

论文名称: DeCUR: decoupling common & unique representations for multimodal self-supervision Link: https://arxiv.org/abs/2309.05300 Published in: Arxiv 2023 Type: Pretrain Code/Project: h...

Feb 19, 2023 Arxiv

RSICap

数据集名称: RSICap 任务: 遥感图像字幕、图文检索发布时间: 2023 模态: 图像、文本数量: 2585对具有高质量人工注释字幕的图像-文本代码源链接: https://github.com/Lavender105/RSGPT 论文源链接: https://arxiv.org/abs/2307.15266 详细描述: 该数据集为每张图像提供了...

Feb 18, 2023 图文对

Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval

论文名称: Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval 模型架构: VLM Task: Image-text Retrieval Link: https://arxiv.org/abs/2308.12509 Code/Project: https://gith...

Feb 13, 2023 TGRS