no code implementations • EMNLP (nlpbt) 2020 • Xinyu Wang, Xiaowen Sun, Tan Yang, Hongbo Wang
We use the pretrained Multi-Head Attention of BERT to model the text and image.
no code implementations • 27 Sep 2023 • Xiaowen Sun, Jiazhan Feng, Yuxuan Wang, Yuxuan Lai, Xingyu Shen, Dongyan Zhao
In this paper, we focus on the innovative dialog-to-image generation task, where the model synthesizes a high-resolution image aligned with the given dialog context as a response.