Learning Deep Representations of Fine-grained Visual Descriptions.

StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks.

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks.

ControlGAN: Controllable Text-to-Image Generation.

Cycle Text-To-Image GAN with BERT.

Adversarial Synthesis of Human Pose from Text.

Controllable Text-to-Image Generation.

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks.

MirrorGAN: Learning Text-to-image Generation by Redescription.

SwapText: Image Based Texts Transfer in Scenes.

3DLSN: End-to-End Optimization of Scene Layout.

Semantic Object Accuracy for Generative Text-to-Image Synthesis.

Local-Global Video-Text Interactions for Temporal Grounding.

Object-driven Text-to-Image Synthesis via Adversarial Training.

CookGAN: Meal Image Synthesis from Ingredients.