Discriminative Style Learning for Cross-Domain Image Captioning

The cross-domain image captioning, which is trained on a source domain and generalized to other domains, usually faces the large domain shift problem. Although prior work has attempted to leverage both paired source and unpaired target data to minimize this shift, the performance is still unsatisfac...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 27., Seite 1723-1736
1. Verfasser: Yuan, Jin (VerfasserIn)
Weitere Verfasser: Zhu, Shuai, Huang, Shuyin, Zhang, Hanwang, Xiao, Yaoqiang, Li, Zhiyong, Wang, Meng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article