Skip to content
forked from joeyz0z/ConZIC

Implementation of "IConZIC : Image-Conditioned Zero-shot Image Captioning by Vision-Language Pre-Training Model", Korea University COSE461 Term Project

License

Notifications You must be signed in to change notification settings

JeonSeongHu/IConZIC

 
 

Repository files navigation

IConZIC : Image-Conditioned Zero-shot Image Captioning by Vision-Language Pre-Trained Model

[Korea University COSE461 Final Project]


Seonghu Jeon, Jiwon Jeong, Byungwoo Jeon. Seongmin Ko

Framework

Results

Acknowledgment

This code is based on the bert-gen, MAGIC and ConZIC

About

Implementation of "IConZIC : Image-Conditioned Zero-shot Image Captioning by Vision-Language Pre-Training Model", Korea University COSE461 Term Project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Languages

  • Jupyter Notebook 96.9%
  • Python 3.1%