1. Generating diverse high-fidelity images with vq-vae-2;razavi;Advances in neural information processing systems,0
2. Zero-shot text-to-image generation;ramesh;ArXiv Preprint,2021
3. Segmentation in style: Unsupervised semantic image segmentation with stylegan and clip;pakhomov;ArXiv Preprint,2021
4. Conditional generative adversarial nets;mirza;ArXiv Preprint,2014
5. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks;lu;ArXiv Preprint,2019