摘要 : In this paper, we concentrate on the text-to-image synthesis task that aims at automatically producing perceptually realistic pictures from text descriptions. Recently, several single-stage methods have been proposed to deal with ... 展开
作者 | Zhang~ Zhenxing Schomaker~ Lambert |
---|---|
作者单位 | |
期刊名称 | 《Neurocomputing》 |
页码/总页数 | 182-198 / 17 |
语种/中图分类号 | 英语 / TP3 |
关键词 | text-to-image generation lack-of-diversity issue single-stage framework generative adversarial network attention mechanism |
DOI | 10.1016/j.neucom.2021.12.005 |
馆藏号 | TP-028 |