Paper Info
Title
Semantically Consistent Text to Fashion Image Synthesis with an enhanced Attentional Generative Adversarial Network
Abstract
•We introduce e-AttnGAN for semantically consistent hierarchical text-to-image synthesis.•An integrated attention module is proposed to relate and transform visual features with language features.•Several enhancements are proposed to improve image quality and text/image similarity while stabilizing the training.•We provide ablation studies on two fashion datasets and show that e-AttnGAN outperforms state-of-the-art models.
Year
DOI
Venue
2020
10.1016/j.patrec.2020.02.030
Pattern Recognition Letters
Keywords
DocType
Volume
Generative adversarial networks,Text-to-Image synthesis,Hierarchical image generation,Image generation,Fashion
Journal
135
ISSN
Citations 
PageRank 
0167-8655
2
0.35
References 
Authors
34
4
Name
Order
Citations
PageRank
Ak, Kenan E.1142.52
Joo-Hwee Lim278382.45
Jo Yew Tham344247.35
Ashraf A. Kassim4116497.26