Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation

Installation:

Please see INSTALL.md. Then

pip install -r requirements.txt
python3 -m spacy download en_core_web_sm

Inference

Obtain the output masks of Val set for CodaLab online evaluation:

cd scripts
sh train_mevis.sh

Inference

cd scripts
sh test_mevis.sh

Models

☁️ Google Drive

Acknowledgement

This project is based on DsHmp and DVIS. Many thanks to the authors for their great works!