DU VLG
method
ID: duvlg
Related Papers
DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
AbstractDue to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation. In this paper, we propose DU-VLG, …...