UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

By Zhu Zhang, Jianxin Ma, Chang Zhou, Rui Men, Zhikang Li, Ming Ding, Jie Tang, Jingren Zhou, Hongxia Yang. 2021

43 citations recorded by the source corpus.

Subfields: Generative Models, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Lu Jiang
2. Ce Liu
3. William T. Freeman
4. Huiwen Chang
5. Han Zhang
6. Eli Shechtman
7. José Lezama
8. Irfan Essa

In Multimodal Learning

1. Ce Liu
2. William T. Freeman
3. Han Zhang
4. Lu Jiang

Citations in the corpus

• MaskGIT: Masked Generative Image Transformer (2022, background): “However, few works have successfully applied the same masked modeling to image generation [53] because of the difficulty in performing autoregressive decoding using bi-directional attentions.”