XGPT: Cross-modal Generative Pre-Training for Image Captioning.
https://arxiv.org/abs/2003.01473
@article{DBLP:journals/corr/abs-2003-01473,
author = {Qiaolin Xia and
Haoyang Huang and
Nan Duan and
Dongdong Zhang and
Lei Ji and
Zhifang Sui and
Edward Cui and
Taroon Bharti and
Xin Liu and
Ming Zhou},
title = {{XGPT:} Cross-modal Generative Pre-Training for Image Captioning},
journal = {CoRR},
volume = {abs/2003.01473},
year = {2020},
url = {https://arxiv.org/abs/2003.01473},
archivePrefix = {arXiv},
eprint = {2003.01473},
timestamp = {Tue, 10 Mar 2020 13:33:48 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-01473.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}