Home

Awesome

MXQ-VAE

Code for the BMVC 2022 paper: "Unconditional Image-Text Pair Generation with Multimodal Cross Quantizer"

<!-- ![architecture](https://user-images.githubusercontent.com/64394696/194465420-edfa0ee8-c54c-4680-a049-699f8b078cc0.png) -->

image

Requirements

pip install -r requirements.txt

Dataset

Caption MNIST

Flower Image-Caption

CUB Image-Caption

Pretrained model

Citation

<!-- If you use any part of this code and pretrained weights for your own purpose, please cite our paper -->