摘要 : Since locally controllable text-to-image generation cannot achieve satisfactory results in detail, a novel locally controllable text-to-image generation network based on visual-linguistic relation alignment is proposed. The goal o... 展开
作者 | Zaike Li Li Liu Huaxiang Zhang Dongmei Liu Yu Song Boqun Li |
---|---|
作者单位 | |
期刊名称 | 《Multimedia Systems》 |
页码/总页数 | 34.1-34.13 / 13 |
语种/中图分类号 | 英语 / TP3 |
关键词 | Text-to-image generation Image-text matching Generative adversarial network Local control |
DOI | 10.1007/s00530-023-01222-7 |
馆藏号 | TP-033 |