Dear participants,
Thank you for joining to the second edition of the DA-VINCIS shared task. We are happy to share with you a starting kit formed by Colab notebooks implementing baseline models that use either text, images or both modalities for approaching the task. Feel free to use them as starting point for your contributions or as complimentary information. Here are links to such baseline models:
1) BETO (text onlu): https://colab.research.google.com/drive/1Xa5cWxGZwZamH_qkmkUlPuFCiSBg97gT?usp=sharing
2) ViT (images only): https://colab.research.google.com/drive/17BuQWJC5rRvgOGfjargp6dL36BGmiw21?usp=sharing
3) Early Fusion of the other two models (multimodal): https://colab.research.google.com/drive/1mg_-Cw9Kp7X5D034nhDtDzjPaDW8EAQT?usp=sharing
Please make a copy of the notebooks in your own drive/git. We hope you find them useful. Looking forward to receiving your submissions!
Best regards
The organizing team,
Posted by: hugojair @ April 18, 2023, 6:44 p.m.