MIST-SMMD:A Spatio-Temporal Information Extraction Method Based on Multimodal Social Media Data

Preprint | Paper

A spatio-temporal information extraction method based on multimodal social media data: A case study on urban inundation
Yilong Wu, Yingjie Chen,Rongyu Zhang, Zhenfei Cui, Xinyi Liu, Jiayi Zhang, Meizhen Wang, Yong Wu^*
Nodata

Discussions about the paper are welcomed in the discussion panel.

Colab demo

Want to run MIST-SMMD with custom image pairs without configuring your own GPU environment? Try the Colab demo:

Installation

Conda:

conda env create -f environment.yaml
conda activate mist

Pip:

pip install -r requirements.txt

Use Tsinghua University Mirrors:

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

The spacy language pack needs to be installed manually:

python -m spacy download zh_core_web_trf

Config File

Changeable configurations are in the config/config.py file, just modify the parameters in config/config.py